adding first version of audio processor

2016-11-30 19:07:19 +01:00
commit 421146fddd
@@ -1,2 +1,10 @@
-# but_emotions_audio
+# up_emotions_audio
 This module aims to extract emotions from audio.  The input argument is either an uploaded audio/video file to the server or a URL. The output is the predicted emotion in terms of Arousal and Valence within the JSON-LD format.
+
+- change the content of the 'rest_vars' pointing to 'classifiers' directory and an empty 'download' directory.
+
+- define the path to the 'rest_vars' in the er/src/com/opensmile/maven/path.java as 'var_file' value.
+
+- change the directory of 'weka' in the 'classifiers/RF_models/run_*.sh'
+
+- if using your own asr, change the bash commands in 'classifiers/asr/*.sh' file to your own asr service.
@@ -0,0 +1,360 @@
+
+///////////////////////////////////////////////////////////////////////////////////////
+///////// > openSMILE configuration file for IS09 emotion challenge< //////////////////
+/////////                                                            //////////////////
+///////// (c) audEERING UG (haftungsbeschränkt),                     //////////////////
+/////////     All rights reserverd.                                  //////////////////
+///////////////////////////////////////////////////////////////////////////////////////
+
+
+///////////////////////////////////////////////////////////////////////////////////////
+;
+; This section is always required in openSMILE configuration files
+;   it configures the componentManager and gives a list of all components which are to be loaded
+; The order in which the components are listed should match 
+;   the order of the data flow for most efficient processing
+;
+///////////////////////////////////////////////////////////////////////////////////////
+[componentInstances:cComponentManager]
+ ; this line configures the default data memory:
+instance[dataMemory].type=cDataMemory
+;instance[waveIn].type=cWaveSource
+instance[fr1].type=cFramer
+instance[pe2].type=cVectorPreemphasis
+instance[w1].type=cWindower
+instance[fft1].type=cTransformFFT
+instance[fftmp1].type=cFFTmagphase
+instance[mspec].type=cMelspec
+instance[mfcc].type=cMfcc
+instance[mzcr].type=cMZcr
+instance[acf].type=cAcf
+instance[cepstrum].type=cAcf
+instance[pitchACF].type=cPitchACF
+instance[energy].type=cEnergy
+instance[lld].type=cContourSmoother
+instance[delta1].type=cDeltaRegression
+instance[functL1].type=cFunctionals
+;instance[arffsink].type=cArffSink
+;instance[mysvmsink].type=cLibsvmLiveSink
+printLevelStats=0
+nThreads=1
+
+/////////////////////////////////////////////////////////////////////////////////////////////
+/////////////////////////   component configuration  ////////////////////////////////////////
+/////////////////////////////////////////////////////////////////////////////////////////////
+; the following sections configure the components listed above
+; a help on configuration parameters can be obtained with 
+;  SMILExtract -H
+; or
+;  SMILExtract -H configTypeName (= componentTypeName)
+/////////////////////////////////////////////////////////////////////////////////////////////
+
+instance[waveIn].type=cWaveSource
+[waveIn:cWaveSource]
+writer.dmLevel=wave
+filename=\cm[inputfile(I){test.wav}:name of input file]
+buffersize=4000
+monoMixdown=1
+
+;instance[portaudioSource].type = cPortaudioSource
+;[portaudioSource:cPortaudioSource]
+;writer.dmLevel = wave
+;monoMixdown = 1
+; ; -1 is the default device
+;device = \cm[device{-1}:portaudio device to use for recording, see -listDevices option]
+;listDevices = \cm[listDevices{0}:add -listDevices 1 to the command-line to see a list available of portaudio devices]
+;sampleRate = \cm[sampleRate{44100}:set the sampling rate in Hz for recording]
+;channels = \cm[channels{2}:set the number of audio channels to record]
+;nBits = 16
+;audioBuffersize_sec = 0.050000
+
+
+[fr1:cFramer]
+reader.dmLevel=wave
+writer.dmLevel=frames
+copyInputName = 1
+noPostEOIprocessing = 1
+frameSize = 0.0250
+frameStep = 0.010
+frameMode = fixed
+frameCenterSpecial = left
+buffersize = 1000
+
+[pe2:cVectorPreemphasis]
+reader.dmLevel=frames
+writer.dmLevel=framespe
+copyInputName = 1
+processArrayFields = 1
+k=0.97
+de = 0
+
+[w1:cWindower]
+reader.dmLevel=framespe
+writer.dmLevel=winframe
+copyInputName = 1
+processArrayFields = 1
+winFunc = ham
+gain = 1.0
+offset = 0
+
+  // ---- LLD -----
+
+[fft1:cTransformFFT]
+reader.dmLevel=winframe
+writer.dmLevel=fftc
+copyInputName = 1
+processArrayFields = 1
+inverse = 0
+
+[fftmp1:cFFTmagphase]
+reader.dmLevel=fftc
+writer.dmLevel=fftmag
+copyInputName = 1
+processArrayFields = 1
+inverse = 0
+magnitude = 1
+phase = 0
+
+[mspec:cMelspec]
+reader.dmLevel=fftmag
+writer.dmLevel=mspec1
+copyInputName = 1
+processArrayFields = 1
+htkcompatible = 1
+nBands = 26
+usePower = 0
+lofreq = 0
+hifreq = 8000
+inverse = 0
+specScale = mel
+
+[mfcc:cMfcc]
+reader.dmLevel=mspec1
+writer.dmLevel=mfcc1
+copyInputName = 1
+processArrayFields = 1
+firstMfcc = 1
+lastMfcc =  12
+cepLifter = 22.0
+htkcompatible = 1
+
+
+[acf:cAcf]
+reader.dmLevel=fftmag
+writer.dmLevel=acf
+nameAppend = acf
+copyInputName = 1
+processArrayFields = 1
+usePower = 1
+cepstrum = 0
+
+[cepstrum:cAcf]
+reader.dmLevel=fftmag
+writer.dmLevel=cepstrum
+nameAppend = acf
+copyInputName = 1
+processArrayFields = 1
+usePower = 1
+cepstrum = 1
+
+[pitchACF:cPitchACF]
+  ; the pitchACF component must ALWAYS read from acf AND cepstrum in the given order!
+reader.dmLevel=acf;cepstrum
+writer.dmLevel=pitch
+copyInputName = 1
+processArrayFields=0
+maxPitch = 500
+voiceProb = 1
+voiceQual = 0
+HNR = 0
+F0 = 1
+F0raw = 0
+F0env = 0
+voicingCutoff = 0.550000
+
+[energy:cEnergy]
+reader.dmLevel=winframe
+writer.dmLevel=energy
+nameAppend=energy
+rms=1
+log=0
+
+[mzcr:cMZcr]
+reader.dmLevel=frames
+writer.dmLevel=mzcr
+copyInputName = 1
+processArrayFields = 1
+zcr = 1
+amax = 0
+mcr = 0
+maxmin = 0
+dc = 0
+
+[lld:cContourSmoother]
+reader.dmLevel=energy;mfcc1;mzcr;pitch
+writer.dmLevel=lld
+writer.levelconf.nT=10
+;writer.levelconf.noHang=2
+writer.levelconf.isRb=0
+writer.levelconf.growDyn=1
+nameAppend = sma
+copyInputName = 1
+noPostEOIprocessing = 0
+smaWin = 3
+
+// ---- delta regression of LLD ----
+[delta1:cDeltaRegression]
+reader.dmLevel=lld
+writer.dmLevel=lld_de
+writer.levelconf.isRb=0
+writer.levelconf.growDyn=1
+nameAppend = de
+copyInputName = 1
+noPostEOIprocessing = 0
+deltawin=2
+blocksize=1
+
+[functL1:cFunctionals]
+reader.dmLevel=lld;lld_de
+writer.dmLevel=func
+copyInputName = 1
+ ; frameSize and frameStep = 0 => functionals over complete input
+ ; (NOTE: buffersize of lld and lld_de levels must be large enough!!)
+frameSize = .50
+frameStep = .25
+frameMode = full
+frameCenterSpecial = left
+functionalsEnabled=Extremes;Regression;Moments
+Extremes.max = 1
+Extremes.min = 1
+Extremes.range = 1
+Extremes.maxpos = 1
+Extremes.minpos = 1
+Extremes.amean = 1
+Extremes.maxameandist = 0
+Extremes.minameandist = 0
+ ; Note: the much better way to normalise the times of maxpos and minpos
+ ; is 'turn', however for compatibility with old files the default 'frame'
+ ; is kept here:
+Extremes.norm = frame
+Regression.linregc1 = 1
+Regression.linregc2 = 1
+Regression.linregerrA = 0
+Regression.linregerrQ = 1
+Regression.qregc1 = 0
+Regression.qregc2 = 0
+Regression.qregc3 = 0
+Regression.qregerrA = 0
+Regression.qregerrQ = 0
+Regression.centroid = 0
+Regression.oldBuggyQerr = 1
+Regression.normInputs = 0
+Regression.normRegCoeff = 0
+Moments.variance = 0
+Moments.stddev = 1
+Moments.skewness = 1
+Moments.kurtosis = 1
+Moments.amean = 0
+
+;;;;;;;;; prepare features for standard output module
+
+
+
+
+
+;; NOTE: no concattenation to levels lld, lld_de and func needed,
+;; as data are already saved correctly in these levels
+
+
+/*[myFS:cDataSelector]
+reader.dmLevel=functionalsA;functionalsB;functionalsNz;functionalsF0;functionalsLLD;functionalsDelta
+writer.dmLevel=selectedFs
+selFile=C:\Users\sag\Dropbox\Databases\BerlinSpeechEmotionDatabase\matlab\RF_FS_170_text.txt
+
+[myclibsvm:cLibsvmSink]
+reader.dmLevel=selectedFs
+filename=smileoutput.lsvm
+* /
+
+ ;;\{standard_data_output.conf.inc}
+
+instance[lldcsv].type=cCsvSink
+[lldcsv:cCsvSink]
+%reader.dmLevel = lld_nzsmo;lldA_smo;lldB_smo;lld_nzsmo_de;lldA_smo_de;lldB_smo_de
+;reader.dmLevel=functionalsA;functionalsB;functionalsNz;functionalsF0;functionalsLLD;functionalsDelta
+reader.dmLevel=func
+filename=\cm[output(O){output.csv}:output csv file for lld, set to a filename to enable lld output]
+append = 1
+delimChar =,
+timestamp = 0
+number = 0
+printHeader = 1
+
+/* ***********************
+ * old data output config, obsoleted by standard_data_output.conf.inc
+
+
+  //////////////////////////////////////////////////////////////////////
+ ///////////////////  data output configuration  //////////////////////
+//////////////////////////////////////////////////////////////////////
+
+// ----- you might need to customise the arff output to suit your needs: ------
+*/
+
+[componentInstances:cComponentManager]
+instance[arffsink].type=cArffSink
+
+[arffsink:cArffSink]
+reader.dmLevel=func
+ ; do not print "frameNumber" attribute to ARFF file
+frameIndex = 0
+frameTime = 0
+ ; name of output file as commandline option
+filename=\cm[arffout(O){output.arff}:name of WEKA Arff output file]
+ ; name of @relation in the ARFF file
+relation=\cm[corpus{SMILEfeatures}:corpus name, arff relation]
+ 
+ ; name of the current instance (usually file name of input wave file)
+;instanceName=\cm[instname(N){noname}:name of arff instance]
+ ;; use this line instead of the above to always set the instance name to the
+ ;; name of the input wave file
+ ;instanceName=\cm[inputfile]
+
+ ; name of class label
+class[0].name = age
+ ; list of nominal classes OR "numeric"
+class[0].type = numeric // \cm[classes{Male,Female}:all classes for arff file attribute]
+ ; the class label or value for the current instance
+target[0].all = \cm[classlabel(a){0}:instance class label]
+ ; append to an existing file, so multiple calls of SMILExtract on different
+ ; input files append to the same output ARFF file
+append=0
+
+/*
+
+[mysvmsink:cLibsvmLiveSink]
+;;reader.dmLevel=functionalsA;functionalsB;functionalsNz;functionalsF0;functionalsLLD;functionalsDelta
+reader.dmLevel=func
+;fselection[0]=models/select_features_before_map.txt
+;mapVector[0]=models/subscapce_1_mapper.txt
+;znorm[0]=models/Znorm_VAM.norm
+;model[1]=models/subscapce_2.model
+;scale[1]=models/subscapce_2.scale
+;mapVector[1]=models/subscapce_2_mapper.txt
+;znorm[1]=models/Znorm_VAM.norm
+;model[2]=models/subscapce_3.model
+;scale[2]=models/subscapce_3.scale
+;mapVector[2]=models/subscapce_3_mapper.txt
+;znorm[2]=models/Znorm_VAM.norm
+printResult=1
+multiModelMode=0
+;classes[0]=classnames.txt
+;predictProbability=1
+;resultRecp=random
+;model=svm.model
+;scale=svm.scale
+model=/home/sag/work/ME/platform_smilextract2/svmarousal.model
+scale=/home/sag/work/ME/platform_smilextract2/svmarousal.scale
+;model=svmarousal.model
+;scale=svmarousal.scale
+*/
@@ -0,0 +1,360 @@
+
+///////////////////////////////////////////////////////////////////////////////////////
+///////// > openSMILE configuration file for IS09 emotion challenge< //////////////////
+/////////                                                            //////////////////
+///////// (c) audEERING UG (haftungsbeschränkt),                     //////////////////
+/////////     All rights reserverd.                                  //////////////////
+///////////////////////////////////////////////////////////////////////////////////////
+
+
+///////////////////////////////////////////////////////////////////////////////////////
+;
+; This section is always required in openSMILE configuration files
+;   it configures the componentManager and gives a list of all components which are to be loaded
+; The order in which the components are listed should match 
+;   the order of the data flow for most efficient processing
+;
+///////////////////////////////////////////////////////////////////////////////////////
+[componentInstances:cComponentManager]
+ ; this line configures the default data memory:
+instance[dataMemory].type=cDataMemory
+;instance[waveIn].type=cWaveSource
+instance[fr1].type=cFramer
+instance[pe2].type=cVectorPreemphasis
+instance[w1].type=cWindower
+instance[fft1].type=cTransformFFT
+instance[fftmp1].type=cFFTmagphase
+instance[mspec].type=cMelspec
+instance[mfcc].type=cMfcc
+instance[mzcr].type=cMZcr
+instance[acf].type=cAcf
+instance[cepstrum].type=cAcf
+instance[pitchACF].type=cPitchACF
+instance[energy].type=cEnergy
+instance[lld].type=cContourSmoother
+instance[delta1].type=cDeltaRegression
+instance[functL1].type=cFunctionals
+;instance[arffsink].type=cArffSink
+;instance[mysvmsink].type=cLibsvmLiveSink
+printLevelStats=0
+nThreads=1
+
+/////////////////////////////////////////////////////////////////////////////////////////////
+/////////////////////////   component configuration  ////////////////////////////////////////
+/////////////////////////////////////////////////////////////////////////////////////////////
+; the following sections configure the components listed above
+; a help on configuration parameters can be obtained with 
+;  SMILExtract -H
+; or
+;  SMILExtract -H configTypeName (= componentTypeName)
+/////////////////////////////////////////////////////////////////////////////////////////////
+
+instance[waveIn].type=cWaveSource
+[waveIn:cWaveSource]
+writer.dmLevel=wave
+filename=\cm[inputfile(I){test.wav}:name of input file]
+buffersize=4000
+monoMixdown=1
+
+;instance[portaudioSource].type = cPortaudioSource
+;[portaudioSource:cPortaudioSource]
+;writer.dmLevel = wave
+;monoMixdown = 1
+; ; -1 is the default device
+;device = \cm[device{-1}:portaudio device to use for recording, see -listDevices option]
+;listDevices = \cm[listDevices{0}:add -listDevices 1 to the command-line to see a list available of portaudio devices]
+;sampleRate = \cm[sampleRate{44100}:set the sampling rate in Hz for recording]
+;channels = \cm[channels{2}:set the number of audio channels to record]
+;nBits = 16
+;audioBuffersize_sec = 0.050000
+
+
+[fr1:cFramer]
+reader.dmLevel=wave
+writer.dmLevel=frames
+copyInputName = 1
+noPostEOIprocessing = 1
+frameSize = 0.0250
+frameStep = 0.010
+frameMode = fixed
+frameCenterSpecial = left
+buffersize = 1000
+
+[pe2:cVectorPreemphasis]
+reader.dmLevel=frames
+writer.dmLevel=framespe
+copyInputName = 1
+processArrayFields = 1
+k=0.97
+de = 0
+
+[w1:cWindower]
+reader.dmLevel=framespe
+writer.dmLevel=winframe
+copyInputName = 1
+processArrayFields = 1
+winFunc = ham
+gain = 1.0
+offset = 0
+
+  // ---- LLD -----
+
+[fft1:cTransformFFT]
+reader.dmLevel=winframe
+writer.dmLevel=fftc
+copyInputName = 1
+processArrayFields = 1
+inverse = 0
+
+[fftmp1:cFFTmagphase]
+reader.dmLevel=fftc
+writer.dmLevel=fftmag
+copyInputName = 1
+processArrayFields = 1
+inverse = 0
+magnitude = 1
+phase = 0
+
+[mspec:cMelspec]
+reader.dmLevel=fftmag
+writer.dmLevel=mspec1
+copyInputName = 1
+processArrayFields = 1
+htkcompatible = 1
+nBands = 26
+usePower = 0
+lofreq = 0
+hifreq = 8000
+inverse = 0
+specScale = mel
+
+[mfcc:cMfcc]
+reader.dmLevel=mspec1
+writer.dmLevel=mfcc1
+copyInputName = 1
+processArrayFields = 1
+firstMfcc = 1
+lastMfcc =  12
+cepLifter = 22.0
+htkcompatible = 1
+
+
+[acf:cAcf]
+reader.dmLevel=fftmag
+writer.dmLevel=acf
+nameAppend = acf
+copyInputName = 1
+processArrayFields = 1
+usePower = 1
+cepstrum = 0
+
+[cepstrum:cAcf]
+reader.dmLevel=fftmag
+writer.dmLevel=cepstrum
+nameAppend = acf
+copyInputName = 1
+processArrayFields = 1
+usePower = 1
+cepstrum = 1
+
+[pitchACF:cPitchACF]
+  ; the pitchACF component must ALWAYS read from acf AND cepstrum in the given order!
+reader.dmLevel=acf;cepstrum
+writer.dmLevel=pitch
+copyInputName = 1
+processArrayFields=0
+maxPitch = 500
+voiceProb = 1
+voiceQual = 0
+HNR = 0
+F0 = 1
+F0raw = 0
+F0env = 0
+voicingCutoff = 0.550000
+
+[energy:cEnergy]
+reader.dmLevel=winframe
+writer.dmLevel=energy
+nameAppend=energy
+rms=1
+log=0
+
+[mzcr:cMZcr]
+reader.dmLevel=frames
+writer.dmLevel=mzcr
+copyInputName = 1
+processArrayFields = 1
+zcr = 1
+amax = 0
+mcr = 0
+maxmin = 0
+dc = 0
+
+[lld:cContourSmoother]
+reader.dmLevel=energy;mfcc1;mzcr;pitch
+writer.dmLevel=lld
+writer.levelconf.nT=10
+;writer.levelconf.noHang=2
+writer.levelconf.isRb=0
+writer.levelconf.growDyn=1
+nameAppend = sma
+copyInputName = 1
+noPostEOIprocessing = 0
+smaWin = 3
+
+// ---- delta regression of LLD ----
+[delta1:cDeltaRegression]
+reader.dmLevel=lld
+writer.dmLevel=lld_de
+writer.levelconf.isRb=0
+writer.levelconf.growDyn=1
+nameAppend = de
+copyInputName = 1
+noPostEOIprocessing = 0
+deltawin=2
+blocksize=1
+
+[functL1:cFunctionals]
+reader.dmLevel=lld;lld_de
+writer.dmLevel=func
+copyInputName = 1
+ ; frameSize and frameStep = 0 => functionals over complete input
+ ; (NOTE: buffersize of lld and lld_de levels must be large enough!!)
+frameSize = .50
+frameStep = .25
+frameMode = full
+frameCenterSpecial = left
+functionalsEnabled=Extremes;Regression;Moments
+Extremes.max = 1
+Extremes.min = 1
+Extremes.range = 1
+Extremes.maxpos = 1
+Extremes.minpos = 1
+Extremes.amean = 1
+Extremes.maxameandist = 0
+Extremes.minameandist = 0
+ ; Note: the much better way to normalise the times of maxpos and minpos
+ ; is 'turn', however for compatibility with old files the default 'frame'
+ ; is kept here:
+Extremes.norm = frame
+Regression.linregc1 = 1
+Regression.linregc2 = 1
+Regression.linregerrA = 0
+Regression.linregerrQ = 1
+Regression.qregc1 = 0
+Regression.qregc2 = 0
+Regression.qregc3 = 0
+Regression.qregerrA = 0
+Regression.qregerrQ = 0
+Regression.centroid = 0
+Regression.oldBuggyQerr = 1
+Regression.normInputs = 0
+Regression.normRegCoeff = 0
+Moments.variance = 0
+Moments.stddev = 1
+Moments.skewness = 1
+Moments.kurtosis = 1
+Moments.amean = 0
+
+;;;;;;;;; prepare features for standard output module
+
+
+
+
+
+;; NOTE: no concattenation to levels lld, lld_de and func needed,
+;; as data are already saved correctly in these levels
+
+
+/*[myFS:cDataSelector]
+reader.dmLevel=functionalsA;functionalsB;functionalsNz;functionalsF0;functionalsLLD;functionalsDelta
+writer.dmLevel=selectedFs
+selFile=C:\Users\sag\Dropbox\Databases\BerlinSpeechEmotionDatabase\matlab\RF_FS_170_text.txt
+
+[myclibsvm:cLibsvmSink]
+reader.dmLevel=selectedFs
+filename=smileoutput.lsvm
+* /
+
+ ;;\{standard_data_output.conf.inc}
+
+instance[lldcsv].type=cCsvSink
+[lldcsv:cCsvSink]
+%reader.dmLevel = lld_nzsmo;lldA_smo;lldB_smo;lld_nzsmo_de;lldA_smo_de;lldB_smo_de
+;reader.dmLevel=functionalsA;functionalsB;functionalsNz;functionalsF0;functionalsLLD;functionalsDelta
+reader.dmLevel=func
+filename=\cm[output(O){output.csv}:output csv file for lld, set to a filename to enable lld output]
+append = 1
+delimChar =,
+timestamp = 0
+number = 0
+printHeader = 1
+
+/* ***********************
+ * old data output config, obsoleted by standard_data_output.conf.inc
+
+
+  //////////////////////////////////////////////////////////////////////
+ ///////////////////  data output configuration  //////////////////////
+//////////////////////////////////////////////////////////////////////
+
+// ----- you might need to customise the arff output to suit your needs: ------
+*/
+
+[componentInstances:cComponentManager]
+instance[arffsink].type=cArffSink
+
+[arffsink:cArffSink]
+reader.dmLevel=func
+ ; do not print "frameNumber" attribute to ARFF file
+frameIndex = 0
+frameTime = 0
+ ; name of output file as commandline option
+filename=\cm[arffout(O){output.arff}:name of WEKA Arff output file]
+ ; name of @relation in the ARFF file
+relation=\cm[corpus{SMILEfeatures}:corpus name, arff relation]
+ 
+ ; name of the current instance (usually file name of input wave file)
+;instanceName=\cm[instname(N){noname}:name of arff instance]
+ ;; use this line instead of the above to always set the instance name to the
+ ;; name of the input wave file
+ ;instanceName=\cm[inputfile]
+
+ ; name of class label
+class[0].name = class
+ ; list of nominal classes OR "numeric"
+class[0].type = {Male,Female} // \cm[classes{Male,Female}:all classes for arff file attribute]
+ ; the class label or value for the current instance
+target[0].all = \cm[classlabel(a){unknown}:instance class label]
+ ; append to an existing file, so multiple calls of SMILExtract on different
+ ; input files append to the same output ARFF file
+append=0
+
+/*
+
+[mysvmsink:cLibsvmLiveSink]
+;;reader.dmLevel=functionalsA;functionalsB;functionalsNz;functionalsF0;functionalsLLD;functionalsDelta
+reader.dmLevel=func
+;fselection[0]=models/select_features_before_map.txt
+;mapVector[0]=models/subscapce_1_mapper.txt
+;znorm[0]=models/Znorm_VAM.norm
+;model[1]=models/subscapce_2.model
+;scale[1]=models/subscapce_2.scale
+;mapVector[1]=models/subscapce_2_mapper.txt
+;znorm[1]=models/Znorm_VAM.norm
+;model[2]=models/subscapce_3.model
+;scale[2]=models/subscapce_3.scale
+;mapVector[2]=models/subscapce_3_mapper.txt
+;znorm[2]=models/Znorm_VAM.norm
+printResult=1
+multiModelMode=0
+;classes[0]=classnames.txt
+;predictProbability=1
+;resultRecp=random
+;model=svm.model
+;scale=svm.scale
+model=/home/sag/work/ME/platform_smilextract2/svmarousal.model
+scale=/home/sag/work/ME/platform_smilextract2/svmarousal.scale
+;model=svmarousal.model
+;scale=svmarousal.scale
+*/
@@ -0,0 +1,388 @@
+@relation dummyarff
+@attribute f_1 numeric
+@attribute f_2 numeric
+@attribute f_3 numeric
+@attribute f_4 numeric
+@attribute f_5 numeric
+@attribute f_6 numeric
+@attribute f_7 numeric
+@attribute f_8 numeric
+@attribute f_9 numeric
+@attribute f_10 numeric
+@attribute f_11 numeric
+@attribute f_12 numeric
+@attribute f_13 numeric
+@attribute f_14 numeric
+@attribute f_15 numeric
+@attribute f_16 numeric
+@attribute f_17 numeric
+@attribute f_18 numeric
+@attribute f_19 numeric
+@attribute f_20 numeric
+@attribute f_21 numeric
+@attribute f_22 numeric
+@attribute f_23 numeric
+@attribute f_24 numeric
+@attribute f_25 numeric
+@attribute f_26 numeric
+@attribute f_27 numeric
+@attribute f_28 numeric
+@attribute f_29 numeric
+@attribute f_30 numeric
+@attribute f_31 numeric
+@attribute f_32 numeric
+@attribute f_33 numeric
+@attribute f_34 numeric
+@attribute f_35 numeric
+@attribute f_36 numeric
+@attribute f_37 numeric
+@attribute f_38 numeric
+@attribute f_39 numeric
+@attribute f_40 numeric
+@attribute f_41 numeric
+@attribute f_42 numeric
+@attribute f_43 numeric
+@attribute f_44 numeric
+@attribute f_45 numeric
+@attribute f_46 numeric
+@attribute f_47 numeric
+@attribute f_48 numeric
+@attribute f_49 numeric
+@attribute f_50 numeric
+@attribute f_51 numeric
+@attribute f_52 numeric
+@attribute f_53 numeric
+@attribute f_54 numeric
+@attribute f_55 numeric
+@attribute f_56 numeric
+@attribute f_57 numeric
+@attribute f_58 numeric
+@attribute f_59 numeric
+@attribute f_60 numeric
+@attribute f_61 numeric
+@attribute f_62 numeric
+@attribute f_63 numeric
+@attribute f_64 numeric
+@attribute f_65 numeric
+@attribute f_66 numeric
+@attribute f_67 numeric
+@attribute f_68 numeric
+@attribute f_69 numeric
+@attribute f_70 numeric
+@attribute f_71 numeric
+@attribute f_72 numeric
+@attribute f_73 numeric
+@attribute f_74 numeric
+@attribute f_75 numeric
+@attribute f_76 numeric
+@attribute f_77 numeric
+@attribute f_78 numeric
+@attribute f_79 numeric
+@attribute f_80 numeric
+@attribute f_81 numeric
+@attribute f_82 numeric
+@attribute f_83 numeric
+@attribute f_84 numeric
+@attribute f_85 numeric
+@attribute f_86 numeric
+@attribute f_87 numeric
+@attribute f_88 numeric
+@attribute f_89 numeric
+@attribute f_90 numeric
+@attribute f_91 numeric
+@attribute f_92 numeric
+@attribute f_93 numeric
+@attribute f_94 numeric
+@attribute f_95 numeric
+@attribute f_96 numeric
+@attribute f_97 numeric
+@attribute f_98 numeric
+@attribute f_99 numeric
+@attribute f_100 numeric
+@attribute f_101 numeric
+@attribute f_102 numeric
+@attribute f_103 numeric
+@attribute f_104 numeric
+@attribute f_105 numeric
+@attribute f_106 numeric
+@attribute f_107 numeric
+@attribute f_108 numeric
+@attribute f_109 numeric
+@attribute f_110 numeric
+@attribute f_111 numeric
+@attribute f_112 numeric
+@attribute f_113 numeric
+@attribute f_114 numeric
+@attribute f_115 numeric
+@attribute f_116 numeric
+@attribute f_117 numeric
+@attribute f_118 numeric
+@attribute f_119 numeric
+@attribute f_120 numeric
+@attribute f_121 numeric
+@attribute f_122 numeric
+@attribute f_123 numeric
+@attribute f_124 numeric
+@attribute f_125 numeric
+@attribute f_126 numeric
+@attribute f_127 numeric
+@attribute f_128 numeric
+@attribute f_129 numeric
+@attribute f_130 numeric
+@attribute f_131 numeric
+@attribute f_132 numeric
+@attribute f_133 numeric
+@attribute f_134 numeric
+@attribute f_135 numeric
+@attribute f_136 numeric
+@attribute f_137 numeric
+@attribute f_138 numeric
+@attribute f_139 numeric
+@attribute f_140 numeric
+@attribute f_141 numeric
+@attribute f_142 numeric
+@attribute f_143 numeric
+@attribute f_144 numeric
+@attribute f_145 numeric
+@attribute f_146 numeric
+@attribute f_147 numeric
+@attribute f_148 numeric
+@attribute f_149 numeric
+@attribute f_150 numeric
+@attribute f_151 numeric
+@attribute f_152 numeric
+@attribute f_153 numeric
+@attribute f_154 numeric
+@attribute f_155 numeric
+@attribute f_156 numeric
+@attribute f_157 numeric
+@attribute f_158 numeric
+@attribute f_159 numeric
+@attribute f_160 numeric
+@attribute f_161 numeric
+@attribute f_162 numeric
+@attribute f_163 numeric
+@attribute f_164 numeric
+@attribute f_165 numeric
+@attribute f_166 numeric
+@attribute f_167 numeric
+@attribute f_168 numeric
+@attribute f_169 numeric
+@attribute f_170 numeric
+@attribute f_171 numeric
+@attribute f_172 numeric
+@attribute f_173 numeric
+@attribute f_174 numeric
+@attribute f_175 numeric
+@attribute f_176 numeric
+@attribute f_177 numeric
+@attribute f_178 numeric
+@attribute f_179 numeric
+@attribute f_180 numeric
+@attribute f_181 numeric
+@attribute f_182 numeric
+@attribute f_183 numeric
+@attribute f_184 numeric
+@attribute f_185 numeric
+@attribute f_186 numeric
+@attribute f_187 numeric
+@attribute f_188 numeric
+@attribute f_189 numeric
+@attribute f_190 numeric
+@attribute f_191 numeric
+@attribute f_192 numeric
+@attribute f_193 numeric
+@attribute f_194 numeric
+@attribute f_195 numeric
+@attribute f_196 numeric
+@attribute f_197 numeric
+@attribute f_198 numeric
+@attribute f_199 numeric
+@attribute f_200 numeric
+@attribute f_201 numeric
+@attribute f_202 numeric
+@attribute f_203 numeric
+@attribute f_204 numeric
+@attribute f_205 numeric
+@attribute f_206 numeric
+@attribute f_207 numeric
+@attribute f_208 numeric
+@attribute f_209 numeric
+@attribute f_210 numeric
+@attribute f_211 numeric
+@attribute f_212 numeric
+@attribute f_213 numeric
+@attribute f_214 numeric
+@attribute f_215 numeric
+@attribute f_216 numeric
+@attribute f_217 numeric
+@attribute f_218 numeric
+@attribute f_219 numeric
+@attribute f_220 numeric
+@attribute f_221 numeric
+@attribute f_222 numeric
+@attribute f_223 numeric
+@attribute f_224 numeric
+@attribute f_225 numeric
+@attribute f_226 numeric
+@attribute f_227 numeric
+@attribute f_228 numeric
+@attribute f_229 numeric
+@attribute f_230 numeric
+@attribute f_231 numeric
+@attribute f_232 numeric
+@attribute f_233 numeric
+@attribute f_234 numeric
+@attribute f_235 numeric
+@attribute f_236 numeric
+@attribute f_237 numeric
+@attribute f_238 numeric
+@attribute f_239 numeric
+@attribute f_240 numeric
+@attribute f_241 numeric
+@attribute f_242 numeric
+@attribute f_243 numeric
+@attribute f_244 numeric
+@attribute f_245 numeric
+@attribute f_246 numeric
+@attribute f_247 numeric
+@attribute f_248 numeric
+@attribute f_249 numeric
+@attribute f_250 numeric
+@attribute f_251 numeric
+@attribute f_252 numeric
+@attribute f_253 numeric
+@attribute f_254 numeric
+@attribute f_255 numeric
+@attribute f_256 numeric
+@attribute f_257 numeric
+@attribute f_258 numeric
+@attribute f_259 numeric
+@attribute f_260 numeric
+@attribute f_261 numeric
+@attribute f_262 numeric
+@attribute f_263 numeric
+@attribute f_264 numeric
+@attribute f_265 numeric
+@attribute f_266 numeric
+@attribute f_267 numeric
+@attribute f_268 numeric
+@attribute f_269 numeric
+@attribute f_270 numeric
+@attribute f_271 numeric
+@attribute f_272 numeric
+@attribute f_273 numeric
+@attribute f_274 numeric
+@attribute f_275 numeric
+@attribute f_276 numeric
+@attribute f_277 numeric
+@attribute f_278 numeric
+@attribute f_279 numeric
+@attribute f_280 numeric
+@attribute f_281 numeric
+@attribute f_282 numeric
+@attribute f_283 numeric
+@attribute f_284 numeric
+@attribute f_285 numeric
+@attribute f_286 numeric
+@attribute f_287 numeric
+@attribute f_288 numeric
+@attribute f_289 numeric
+@attribute f_290 numeric
+@attribute f_291 numeric
+@attribute f_292 numeric
+@attribute f_293 numeric
+@attribute f_294 numeric
+@attribute f_295 numeric
+@attribute f_296 numeric
+@attribute f_297 numeric
+@attribute f_298 numeric
+@attribute f_299 numeric
+@attribute f_300 numeric
+@attribute f_301 numeric
+@attribute f_302 numeric
+@attribute f_303 numeric
+@attribute f_304 numeric
+@attribute f_305 numeric
+@attribute f_306 numeric
+@attribute f_307 numeric
+@attribute f_308 numeric
+@attribute f_309 numeric
+@attribute f_310 numeric
+@attribute f_311 numeric
+@attribute f_312 numeric
+@attribute f_313 numeric
+@attribute f_314 numeric
+@attribute f_315 numeric
+@attribute f_316 numeric
+@attribute f_317 numeric
+@attribute f_318 numeric
+@attribute f_319 numeric
+@attribute f_320 numeric
+@attribute f_321 numeric
+@attribute f_322 numeric
+@attribute f_323 numeric
+@attribute f_324 numeric
+@attribute f_325 numeric
+@attribute f_326 numeric
+@attribute f_327 numeric
+@attribute f_328 numeric
+@attribute f_329 numeric
+@attribute f_330 numeric
+@attribute f_331 numeric
+@attribute f_332 numeric
+@attribute f_333 numeric
+@attribute f_334 numeric
+@attribute f_335 numeric
+@attribute f_336 numeric
+@attribute f_337 numeric
+@attribute f_338 numeric
+@attribute f_339 numeric
+@attribute f_340 numeric
+@attribute f_341 numeric
+@attribute f_342 numeric
+@attribute f_343 numeric
+@attribute f_344 numeric
+@attribute f_345 numeric
+@attribute f_346 numeric
+@attribute f_347 numeric
+@attribute f_348 numeric
+@attribute f_349 numeric
+@attribute f_350 numeric
+@attribute f_351 numeric
+@attribute f_352 numeric
+@attribute f_353 numeric
+@attribute f_354 numeric
+@attribute f_355 numeric
+@attribute f_356 numeric
+@attribute f_357 numeric
+@attribute f_358 numeric
+@attribute f_359 numeric
+@attribute f_360 numeric
+@attribute f_361 numeric
+@attribute f_362 numeric
+@attribute f_363 numeric
+@attribute f_364 numeric
+@attribute f_365 numeric
+@attribute f_366 numeric
+@attribute f_367 numeric
+@attribute f_368 numeric
+@attribute f_369 numeric
+@attribute f_370 numeric
+@attribute f_371 numeric
+@attribute f_372 numeric
+@attribute f_373 numeric
+@attribute f_374 numeric
+@attribute f_375 numeric
+@attribute f_376 numeric
+@attribute f_377 numeric
+@attribute f_378 numeric
+@attribute f_379 numeric
+@attribute f_380 numeric
+@attribute f_381 numeric
+@attribute f_382 numeric
+@attribute f_383 numeric
+@attribute f_384 numeric
+@attribute class {1,0} 
+@data
+5.481e-02, 4.606e-06, 5.480e-02,       144,       012, 7.055e-03,-1.097e-05, 8.756e-03, 1.344e-04, 1.163e-02, 2.092e+00, 6.938e+00, 5.182e+00,-1.851e+01, 2.369e+01,       104,       181,-8.808e+00,-6.492e-03,-7.802e+00, 2.869e+01, 5.388e+00, 5.336e-01, 2.204e+00, 1.158e+01,-2.539e+01, 3.697e+01,       139,       096,-8.787e+00, 7.992e-03,-1.003e+01, 4.901e+01, 7.038e+00, 3.089e-01, 3.281e+00, 3.719e+00,-2.125e+01, 2.497e+01,       012,       106,-6.748e+00,-1.777e-02,-3.994e+00, 1.887e+01, 4.627e+00,-3.462e-01, 3.303e+00, 6.074e+00,-2.513e+01, 3.121e+01,       095,       188,-9.836e+00,-5.469e-03,-8.988e+00, 3.117e+01, 5.604e+00,-5.683e-02, 3.857e+00, 5.864e+00,-2.201e+01, 2.787e+01,       016,       135,-7.781e+00,-2.141e-03,-7.449e+00, 2.368e+01, 4.870e+00,-2.813e-01, 3.972e+00, 7.598e+00,-3.077e+01, 3.837e+01,       000,       112,-8.026e+00,-1.732e-03,-7.758e+00, 6.137e+01, 7.835e+00,-5.113e-01, 2.744e+00, 2.057e+01,-1.481e+01, 3.538e+01,       145,       201,-2.547e+00, 4.904e-03,-3.307e+00, 3.132e+01, 5.613e+00, 8.411e-01, 4.966e+00, 6.758e+00,-2.790e+01, 3.465e+01,       016,       198,-7.219e+00, 1.072e-02,-8.881e+00, 5.183e+01, 7.263e+00,-6.403e-01, 3.128e+00, 1.398e+01,-1.819e+01, 3.217e+01,       186,       123,-3.447e+00,-4.000e-03,-2.827e+00, 4.056e+01, 6.379e+00,-1.716e-01, 2.500e+00, 8.664e+00,-1.635e+01, 2.501e+01,       016,       133,-4.963e+00, 7.083e-04,-5.072e+00, 2.645e+01, 5.144e+00, 2.141e-01, 2.701e+00, 6.540e+00,-2.396e+01, 3.050e+01,       053,       114,-4.389e+00,-1.066e-03,-4.224e+00, 3.412e+01, 5.842e+00,-7.047e-01, 3.463e+00, 7.308e+00,-1.196e+01, 1.927e+01,       185,       202,-1.797e+00,-7.741e-03,-5.974e-01, 1.110e+01, 3.403e+00,-8.518e-02, 3.553e+00, 4.100e-01,       000, 4.100e-01,       045,       012, 1.917e-01,-6.452e-05, 2.017e-01, 8.687e-03, 9.338e-02, 6.979e-02, 2.469e+00, 8.253e-01, 9.177e-02, 7.335e-01,       118,       000, 3.432e-01,-3.257e-04, 3.937e-01, 2.852e-02, 1.714e-01, 1.158e+00, 3.268e+00, 2.500e+02,       000, 2.500e+02,       130,       000, 2.861e+01,-4.906e-02, 3.622e+01, 4.021e+03, 6.357e+01, 2.034e+00, 5.621e+00, 1.356e-02,-9.137e-03, 2.269e-02,       142,       148, 7.993e-07,-8.558e-07, 1.334e-04, 5.900e-06, 2.430e-03, 6.482e-01, 1.052e+01, 2.860e+00,-4.245e+00, 7.105e+00,       011,       017,-2.695e-02,-2.253e-04, 7.963e-03, 9.443e-01, 9.720e-01,-5.061e-01, 7.270e+00, 4.488e+00,-6.839e+00, 1.133e+01,       102,       141,-1.484e-02, 7.416e-04,-1.298e-01, 2.150e+00, 1.468e+00,-1.126e+00, 7.426e+00, 4.936e+00,-3.612e+00, 8.548e+00,       108,       181,-4.358e-03, 1.173e-04,-2.253e-02, 1.264e+00, 1.124e+00,-3.539e-02, 5.470e+00, 4.277e+00,-3.588e+00, 7.865e+00,       010,       205, 6.592e-04, 1.662e-04,-2.510e-02, 1.517e+00, 1.232e+00, 1.044e-01, 3.956e+00, 4.076e+00,-4.117e+00, 8.193e+00,       011,       129,-5.497e-03, 2.940e-04,-5.107e-02, 1.472e+00, 1.214e+00, 2.687e-01, 3.945e+00, 3.310e+00,-3.488e+00, 6.797e+00,       044,       018,-3.514e-02, 1.224e-03,-2.249e-01, 1.541e+00, 1.246e+00,-8.662e-02, 2.998e+00, 8.032e+00,-4.897e+00, 1.293e+01,       142,       089,-2.351e-02, 1.891e-04,-5.282e-02, 3.030e+00, 1.741e+00, 6.297e-01, 5.315e+00, 5.344e+00,-4.723e+00, 1.007e+01,       010,       185, 4.236e-02, 7.850e-05, 3.019e-02, 2.345e+00, 1.531e+00, 1.724e-01, 3.861e+00, 3.847e+00,-4.187e+00, 8.034e+00,       183,       202,-1.226e-02, 1.134e-03,-1.881e-01, 1.899e+00, 1.382e+00,-2.586e-01, 3.350e+00, 3.451e+00,-2.983e+00, 6.434e+00,       086,       042,-1.885e-02, 6.875e-04,-1.254e-01, 1.510e+00, 1.230e+00,-9.086e-03, 2.685e+00, 4.109e+00,-4.784e+00, 8.893e+00,       116,       111,-4.909e-03, 1.465e-04,-2.762e-02, 1.865e+00, 1.366e+00, 4.457e-02, 3.489e+00, 2.745e+00,-3.958e+00, 6.702e+00,       118,       199,-1.772e-02, 2.621e-04,-5.835e-02, 9.258e-01, 9.625e-01,-1.912e-01, 4.191e+00, 6.667e-02,-4.317e-02, 1.098e-01,       018,       197, 7.229e-04,-8.015e-06, 1.965e-03, 2.493e-04, 1.581e-02, 5.324e-01, 4.889e+00, 1.017e-01,-1.177e-01, 2.193e-01,       144,       140, 3.463e-04,-2.074e-05, 3.560e-03, 1.044e-03, 3.237e-02, 1.454e-01, 4.819e+00, 6.676e+01,-5.932e+01, 1.261e+02,       129,       121, 1.459e-08,-3.550e-03, 5.503e-01, 2.380e+02, 1.543e+01, 3.217e-01, 8.951e+00,0
@@ -0,0 +1,10 @@
+#!/bin/bash
+export CLASSPATH=$CLASSPATH:/home/sag/Softwares/weka-3-8-0/weka.jar
+NEW_UUID=$(date | md5sum | awk '{ print substr( $0, 1, 10 ) }')'a.arff'
+#NEW_UUID=$(cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w 12 | head -n 1)'.arff'
+./SMILExtract -C IS09_emotion_Agreeable.conf -I $1 -l 0 -classlabel 0 -O $NEW_UUID
+res=$(java weka.classifiers.trees.RandomForest -T  $NEW_UUID -l Agreeable.model -classifications weka.classifiers.evaluation.output.prediction.PlainText | grep 1 | tr -s ' ' | sed -r 's/^ //g' | cut -d' ' -f3)
+#| sed -r 's/^/class=/g'
+printf '{"PROCESSOR":"OpenSMILE","ORIGIN":"libsvm","TYPE":"regression","COMPONENT":"mysvmsink","VIDX":1,"VALUE":'$res',"PROB":[{"CONFIDENCE":1.00}]}\n'
+#rm $NEW_UUID
+
@@ -0,0 +1,10 @@
+#!/bin/bash
+export CLASSPATH=$CLASSPATH:/home/sag/Softwares/weka-3-8-0/weka.jar
+NEW_UUID=$(date | md5sum | awk '{ print substr( $0, 1, 10 ) }')'a.arff'
+#NEW_UUID=$(cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w 12 | head -n 1)'.arff'
+./SMILExtract -C IS09_emotion_Concious.conf -I $1 -l 0 -classlabel 0 -O $NEW_UUID
+res=$(java weka.classifiers.trees.RandomForest -T  $NEW_UUID -l Concious.model -classifications weka.classifiers.evaluation.output.prediction.PlainText | grep 1 | tr -s ' ' | sed -r 's/^ //g' | cut -d' ' -f3)
+#| sed -r 's/^/class=/g'
+printf '{"PROCESSOR":"OpenSMILE","ORIGIN":"libsvm","TYPE":"regression","COMPONENT":"mysvmsink","VIDX":1,"VALUE":'$res',"PROB":[{"CONFIDENCE":1.00}]}\n'
+#rm $NEW_UUID
+
@@ -0,0 +1,10 @@
+#!/bin/bash
+export CLASSPATH=$CLASSPATH:/home/sag/Softwares/weka-3-8-0/weka.jar
+NEW_UUID=$(date | md5sum | awk '{ print substr( $0, 1, 10 ) }')'a.arff'
+#NEW_UUID=$(cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w 12 | head -n 1)'.arff'
+./SMILExtract -C IS09_emotion_Extroversion.conf -I $1 -l 0 -classlabel 0 -O $NEW_UUID
+res=$(java weka.classifiers.trees.RandomForest -T  $NEW_UUID -l Extroversion.model -classifications weka.classifiers.evaluation.output.prediction.PlainText | grep 1 | tr -s ' ' | sed -r 's/^ //g' | cut -d' ' -f3)
+#| sed -r 's/^/class=/g'
+printf '{"PROCESSOR":"OpenSMILE","ORIGIN":"libsvm","TYPE":"regression","COMPONENT":"mysvmsink","VIDX":1,"VALUE":'$res',"PROB":[{"CONFIDENCE":1.00}]}\n'
+#rm $NEW_UUID
+
@@ -0,0 +1,10 @@
+#!/bin/bash
+export CLASSPATH=$CLASSPATH:/home/sag/Softwares/weka-3-8-0/weka.jar
+NEW_UUID=$(date | md5sum | awk '{ print substr( $0, 1, 10 ) }')'a.arff'
+#NEW_UUID=$(cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w 12 | head -n 1)'.arff'
+./SMILExtract -C IS09_emotion_Neuroticism.conf -I $1 -l 0 -classlabel 0 -O $NEW_UUID
+res=$(java weka.classifiers.trees.RandomForest -T  $NEW_UUID -l Neuroticism.model -classifications weka.classifiers.evaluation.output.prediction.PlainText | grep 1 | tr -s ' ' | sed -r 's/^ //g' | cut -d' ' -f3)
+#| sed -r 's/^/class=/g'
+printf '{"PROCESSOR":"OpenSMILE","ORIGIN":"libsvm","TYPE":"regression","COMPONENT":"mysvmsink","VIDX":1,"VALUE":'$res',"PROB":[{"CONFIDENCE":1.00}]}\n'
+#rm $NEW_UUID
+
@@ -0,0 +1,10 @@
+#!/bin/bash
+export CLASSPATH=$CLASSPATH:/home/sag/Softwares/weka-3-8-0/weka.jar
+NEW_UUID=$(date | md5sum | awk '{ print substr( $0, 1, 10 ) }')'Openness.arff'
+#NEW_UUID=$(cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w 12 | head -n 1)'.arff'
+./SMILExtract -C IS09_emotion_Openness.conf -I $1 -l 5 -classlabel 0 -O $NEW_UUID
+res=$(java weka.classifiers.trees.RandomForest -T  $NEW_UUID -l Openness.model -classifications weka.classifiers.evaluation.output.prediction.PlainText | grep 1 | tr -s ' ' | sed -r 's/^ //g' | cut -d' ' -f3)
+#| sed -r 's/^/class=/g'
+printf '{"PROCESSOR":"OpenSMILE","ORIGIN":"libsvm","TYPE":"regression","COMPONENT":"mysvmsink","VIDX":1,"VALUE":'$res',"PROB":[{"CONFIDENCE":1.00}]}\n'
+rm $NEW_UUID
+
@@ -0,0 +1,10 @@
+#!/bin/bash
+export CLASSPATH=$CLASSPATH:/path/to/weka-3-8-0/weka.jar
+NEW_UUID=$(date | md5sum | awk '{ print substr( $0, 1, 10 ) }')'a.arff'
+#NEW_UUID=$(cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w 12 | head -n 1)'.arff'
+./SMILExtract -C IS09_emotion_age.conf -I $1 -l 0 -classlabel 0 -O $NEW_UUID
+res=$(java weka.classifiers.functions.SMOreg -T  $NEW_UUID -l age_smoreg.model -classifications weka.classifiers.evaluation.output.prediction.PlainText | grep 1 | tr -s ' ' | sed -r 's/^ //g' | cut -d' ' -f3 |  cut -f1 -d".")
+#| sed -r 's/^/class=/g'
+printf '{"PROCESSOR":"OpenSMILE","ORIGIN":"libsvm","TYPE":"regression","COMPONENT":"mysvmsink","VIDX":1,"VALUE":'$res',"PROB":[{"CONFIDENCE":1.00}]}\n'
+rm $NEW_UUID
+
@@ -0,0 +1,10 @@
+#!/bin/bash
+export CLASSPATH=$CLASSPATH:/home/sag/Softwares/weka-3-8-0/weka.jar
+NEW_UUID=$(date | md5sum | awk '{ print substr( $0, 1, 10 ) }')'a.arff'
+#NEW_UUID=$(cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w 12 | head -n 1)'.arff'
+./SMILExtract -C IS09_emotion_age.conf -I $1 -l 0 -classlabel 0 -O $NEW_UUID
+res=$(java weka.classifiers.functions.SMOreg -T  $NEW_UUID -l age_smoreg.model -classifications weka.classifiers.evaluation.output.prediction.PlainText | grep 1 | tr -s ' ' | sed -r 's/^ //g' | cut -d' ' -f3 |  cut -f1 -d".")
+#| sed -r 's/^/class=/g'
+printf '{"PROCESSOR":"OpenSMILE","ORIGIN":"libsvm","TYPE":"regression","COMPONENT":"mysvmsink","VIDX":1,"VALUE":'$res',"PROB":[{"CONFIDENCE":1.00}]}\n'
+rm $NEW_UUID
+
@@ -0,0 +1,19 @@
+#!/bin/bash
+export CLASSPATH=$CLASSPATH:/path/to/weka-3-8-0/weka.jar
+NEW_UUID=$(date | md5sum | awk '{ print substr( $0, 1, 10 ) }')'g.arff'
+#NEW_UUID=$(cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w 12 | head -n 1)'.arff'
+./SMILExtract -C IS09_emotion_gender.conf -I $1 -l 0 -classlabel Female -O $NEW_UUID
+res=$(java weka.classifiers.trees.RandomForest -T  $NEW_UUID -l gender_rf.model -classifications weka.classifiers.evaluation.output.prediction.PlainText | grep ':' |tr -s ' '|sed -r 's/^ //g'|cut -d' ' -f3|cut -d':' -f2)
+#| sed -r 's/^/class=/g'
+male='Male'
+if [ "$res" = "$male" ];
+then
+printf '{"PROCESSOR":"OpenSMILE","ORIGIN":"libsvm","TYPE":"classification","COMPONENT":"mysvmsink","VIDX":1,"VALUE":"Male","PROB":[{"CLASS_IDX":0,"CLASS_NAME":"Male","CLASS_PROB":1.0},{"CLASS_IDX":1,"CLASS_NAME":"Female","CLASS_PROB":0.0},],}\n'
+fi 
+female='Female'
+if [ "$res" = "$female" ];
+then
+printf '{"PROCESSOR":"OpenSMILE","ORIGIN":"libsvm","TYPE":"classification","COMPONENT":"mysvmsink","VIDX":1,"VALUE":"Female","PROB":[{"CLASS_IDX":0,"CLASS_NAME":"Male","CLASS_PROB":0.0},{"CLASS_IDX":1,"CLASS_NAME":"Female","CLASS_PROB":1.0},],}\n'
+fi
+rm $NEW_UUID
+
@@ -0,0 +1,19 @@
+#!/bin/bash
+export CLASSPATH=$CLASSPATH:/home/sag/Softwares/weka-3-8-0/weka.jar
+NEW_UUID=$(date | md5sum | awk '{ print substr( $0, 1, 10 ) }')'g.arff'
+#NEW_UUID=$(cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w 12 | head -n 1)'.arff'
+./SMILExtract -C IS09_emotion_gender.conf -I $1 -l 0 -classlabel Female -O $NEW_UUID
+res=$(java weka.classifiers.trees.RandomForest -T  $NEW_UUID -l gender_rf.model -classifications weka.classifiers.evaluation.output.prediction.PlainText | grep ':' |tr -s ' '|sed -r 's/^ //g'|cut -d' ' -f3|cut -d':' -f2)
+#| sed -r 's/^/class=/g'
+male='Male'
+if [ "$res" = "$male" ];
+then
+printf '{"PROCESSOR":"OpenSMILE","ORIGIN":"libsvm","TYPE":"classification","COMPONENT":"mysvmsink","VIDX":1,"VALUE":"Male","PROB":[{"CLASS_IDX":0,"CLASS_NAME":"Male","CLASS_PROB":1.0},{"CLASS_IDX":1,"CLASS_NAME":"Female","CLASS_PROB":0.0},],}\n'
+fi 
+female='Female'
+if [ "$res" = "$female" ];
+then
+printf '{"PROCESSOR":"OpenSMILE","ORIGIN":"libsvm","TYPE":"classification","COMPONENT":"mysvmsink","VIDX":1,"VALUE":"Female","PROB":[{"CLASS_IDX":0,"CLASS_NAME":"Male","CLASS_PROB":0.0},{"CLASS_IDX":1,"CLASS_NAME":"Female","CLASS_PROB":1.0},],}\n'
+fi
+rm $NEW_UUID
+
@@ -0,0 +1,12 @@
+#!/bin/bash
+curl --user testuser:testuser  -X GET "http://X.X.X.X:X/technologies/stt?path=$1"
+
+#output form: {"result":{"info":{"id":"ID","state":"waiting"}}}
+#OR once processing is finished:
+#	{"result":{"one_best_result":{"segmentation":[
+#	{"start":1600000,"end":4200000,"word":"<s>"},
+#	{"start":4200000,"end":11100000,"word":"I"},
+#	{“start":11100000,"end":14000000,"word":"AM"},
+#	{"start":14000000,"end":19100000,"word":"FINE"},
+#	{"start":19100000,"end":22800000,"word":"."}}]}}}
+#	Where <s> denotes ‘silence’, and start/end are 0.0000001s → 1600000 = 0.16s
@@ -0,0 +1,5 @@
+#!/bin/bash
+curl --user testuser:testuser  -X GET "http://X.X.X.X:X/technologies/stt?path=$1&model=ENGLISH_L&result_type=one_best"
+
+#output form: {"result":{"info":{"id":"ID","state":"waiting"}}}
+
@@ -0,0 +1,5 @@
+#!/bin/bash
+curl -X POST --data-binary @$1 --user testuser:testuser  http://X.X.X.X:X/audiofile?path=$1
+
+#output form:{"result":{"info":{"name":"FILENAME.wav"}}}
+
@@ -0,0 +1,2 @@
+#!/bin/bash
+curl -X POST --data-binary @$1 --user testuser:testuser  http://X.X.X.X:X/audiofile?path=$1
@@ -0,0 +1,8 @@
+#!/bin/bash
+curl --user testuser:testuser -X GET "http://X.X.X.X:X/pending/$1"
+
+#output form: {"result":{"info":{"id":"ID","state":"waiting"}}}
+#OR
+#{"result":{"info":{"id":"ID","state":"finished"}}}
+
+
@@ -0,0 +1,2 @@
+#!/bin/bash
+curl --user testuser:testuser -X GET "http://X.X.X.X:X/pending/$1"
@@ -0,0 +1,15 @@
+curl -X POST --data-binary @$1 --user testuser:testuser  http://136.243.53.82:8601/audiofile?path=$1
+{"result":{"version":2,"name":"AudioFileInfoResult","info":{"name":"sss.wav","last_modified":"2016-09-19T10:15:18Z","created":"2016-09-19T10:15:18Z","size":79862,"is_directory":false,"frequency":8000,"length":4.988625,"n_channels":1,"format":"lin16"}}}
+
+curl --user testuser:testuser  -X GET "http://136.243.53.82:8601/technologies/stt?path=$1&model=ENGLISH_L&result_type=one_best"
+{"result":{"version":1,"name":"PendingInfoResult","info":{"id":"aaddd257-95f5-4398-9db9-2cabff12d9da","state":"waiting"}}}
+
+curl --user testuser:testuser  -X GET "http://136.243.53.82:8601/pending/73e01038-b0aa-4b46-8011-084829231671"
+{"result":{"version":1,"name":"PendingInfoResult","info":{"id":"aaddd257-95f5-4398-9db9-2cabff12d9da","state":"waiting"}}}
+{"result":{"version":1,"name":"PendingInfoResult","info":{"id":"aaddd257-95f5-4398-9db9-2cabff12d9da","state":"finished"}}}
+
+
+curl -X POST --data-binary @$1 --user testuser:testuser  http://136.243.53.82:8601/audiofile?path=$1
+{"result":{"version":2,"name":"SpeechRecognitionOneBestResult","file":"\/sad2_happy3_8khz.wav","model":"ENGLISH_L","one_best_result":{"segmentation":[{"channel_id":0,"score":-684.55896,"confidence":13382.554,"start":1600000,"end":4200000,"word":"<s>"},{"channel_id":0,"score":-4015.509,"confidence":-97.95257,"start":4200000,"end":11100000,"word":"LIMITED"},{"channel_id":0,"score":-1345.1619,"confidence":-188.62932,"start":11100000,"end":14000000,"word":"IS"},{"channel_id":0,"score":-2018.9628,"confidence":-75.10674,"start":14000000,"end":19100000,"word":"A"},{"channel_id":0,"score":-2227.218,"confidence":-294.19534,"start":19100000,"end":22800000,"word":"<\/s>"},{"channel_id":0,"score":-605.6393,"confidence":10061.17,"start":23200000,"end":25200000,"word":"<s>"},{"channel_id":0,"score":-1929.8737,"confidence":-41.353687,"start":25200000,"end":28300000,"word":"BUT"},{"channel_id":0,"score":-1288.3638,"confidence":-43.10891,"start":28300000,"end":31200000,"word":"NO"},{"channel_id":0,"score":-839.043,"confidence":-42.473152,"start":31200000,"end":32500000,"word":"I"},{"channel_id":0,"score":-1854.2478,"confidence":-85.816895,"start":32500000,"end":35800000,"word":"REALLY"},{"channel_id":0,"score":-5980.855,"confidence":-290.30914,"start":35800000,"end":45400000,"word":"UNHAPPY"},{"channel_id":0,"score":-973.4547,"confidence":-48.923462,"start":45400000,"end":47800000,"word":"<\/s>"}]}}}
+
+
@@ -0,0 +1,15 @@
+#!/bin/bash
+# Arousal and valence prediction using bag-of-audio-words
+
+wavfile=input.wav
+
+#./SMILExtract -C "mfcc_energy.conf" -logfile "smile.log" -I $wavfile -instname $wavfile -csvoutput "LLD.csv" -l 1
+./SMILExtract -C "mfcc_energy.conf" -logfile "smile.log" -I $wavfile -instname $wavfile -csvoutput "LLD.csv" -l 1
+
+java -jar openXBOW.jar -i LLD.csv -attributes nt1111111111111 -o boaw.libsvm -a 10 -norm 1 -b book &>/dev/null
+./predict boaw.libsvm modelArousal.svr arousal.txt &>/dev/null
+./predict boaw.libsvm modelValence.svr valence.txt &>/dev/null
+
+cat arousal.txt
+
+cat valence.txt
@@ -0,0 +1,15 @@
+#!/bin/bash
+# Arousal and valence prediction using bag-of-audio-words
+
+wavfile=input.wav
+
+#./SMILExtract -C "mfcc_energy.conf" -logfile "smile.log" -I $wavfile -instname $wavfile -csvoutput "LLD.csv" -l 1
+./SMILExtract -C "mfcc_energy.conf" -logfile "smile.log" -I $wavfile -instname $wavfile -csvoutput "LLD.csv" -l 1
+
+java -jar openXBOW.jar -i LLD.csv -attributes nt1111111111111 -o boaw.libsvm -a 10 -norm 1 -b book &>/dev/null
+./predict boaw.libsvm modelArousal.svr arousal.txt &>/dev/null
+./predict boaw.libsvm modelValence.svr valence.txt &>/dev/null
+
+cat arousal.txt
+echo 
+cat valence.txt
@@ -0,0 +1,121 @@
+//////////////////////////////////////////////////////////////////////////////
+///////// > openSMILE configuration file mfcc+log-energy <  //////////////////
+///////// (c) audEERING UG (haftungsbeschränkt),            //////////////////
+/////////     All rights reserverd.                         //////////////////
+//////////////////////////////////////////////////////////////////////////////
+
+[componentInstances:cComponentManager]
+instance[dataMemory].type=cDataMemory
+instance[waveIn].type=cWaveSource
+instance[frame].type=cFramer
+instance[pe].type=cVectorPreemphasis
+instance[window].type=cWindower
+
+instance[fft1].type=cTransformFFT
+instance[fftmp1].type=cFFTmagphase
+instance[mspec].type=cMelspec
+instance[mfcc].type=cMfcc
+instance[energy].type=cEnergy
+instance[cat].type=cVectorConcat
+
+instance[csvsink].type=cCsvSink
+nThreads=1
+printLevelStats=0
+
+
+[waveIn:cWaveSource]
+filename=\cm[inputfile(I){test.wav}:name of input file]
+writer.dmLevel=wave
+;buffersize=16000
+monoMixdown=1
+
+[frame:cFramer]
+reader.dmLevel=wave
+writer.dmLevel=frames
+frameSize=0.025
+frameStep=0.010
+;frameCenterSpecial = left
+
+[pe:cVectorPreemphasis]
+reader.dmLevel=frames
+writer.dmLevel=framespe
+k = 0.97
+de = 0
+
+[window:cWindower]
+reader.dmLevel=framespe
+writer.dmLevel=winoutput
+winFunc = ham
+gain = 1.0
+
+[fft1:cTransformFFT]
+reader.dmLevel=winoutput
+writer.dmLevel=fftc
+
+[fftmp1:cFFTmagphase]
+reader.dmLevel=fftc
+writer.dmLevel=fft
+
+[mspec:cMelspec]
+reader.dmLevel=fft
+writer.dmLevel=mspec
+htkcompatible = 1
+nBands = 26
+usePower = 1
+lofreq = 0
+hifreq = 8000
+
+[mfcc:cMfcc]
+reader.dmLevel=mspec
+writer.dmLevel=mfcc
+writer.levelconf.growDyn=1
+writer.levelconf.isRb=0
+buffersize=1000
+firstMfcc = 1
+lastMfcc =  12
+htkcompatible = 1
+
+[energy:cEnergy]
+reader.dmLevel=frames
+writer.dmLevel=energy
+writer.levelconf.growDyn=1
+writer.levelconf.isRb=0
+buffersize=1000
+htkcompatible=1
+
+
+[cat:cVectorConcat]
+reader.dmLevel=mfcc;energy
+writer.dmLevel=ft0
+copyInputName = 1
+processArrayFields = 0
+
+# 
+[delta:cDeltaRegression]
+reader.dmLevel=ft0
+writer.dmLevel=ft0de
+nameAppend = de
+copyInputName = 1
+noPostEOIprocessing = 0
+deltawin=2
+blocksize=1
+
+# 
+[accel:cDeltaRegression]
+reader.dmLevel=ft0de
+writer.dmLevel=ft0dede
+nameAppend = de
+copyInputName = 1
+noPostEOIprocessing = 0
+deltawin=2
+blocksize=1
+
+
+[csvsink:cCsvSink]
+reader.dmLevel = ft0
+filename=\cm[csvoutput{output.csv}:output csv file]
+timestamp = 1
+number = 0
+printHeader = 0
+instanceName=\cm[instname{file}:instance name]
+
@@ -0,0 +1,506 @@
+solver_type L2R_L2LOSS_SVR_DUAL
+nr_class 2
+nr_feature 500
+bias 1
+w
+0.002614424181136787 
+-0.001263899781312691 
+0.001176853648970056 
+0.001337888719553897 
+-0.00101344044061725 
+0.001080949272712622 
+-0.0007599125301275103 
+-0.001566990692356626 
+-0.005612036535450196 
+0.0007763647188360081 
+0.002752688103056981 
+0.002509446446425768 
+0.003616621307520941 
+-0.0004441468157957035 
+7.492634707004078e-005 
+0.0008916282454711916 
+-0.000253261344429788 
+0.0012667487038444 
+0.0007213811047151121 
+0.000584708100406799 
+0.000306959729632193 
+-2.035618299635387e-005 
+0.001626377398542689 
+0.0009363178805822339 
+0.002948781349926091 
+0.0002498420782423684 
+0.0005500270468316948 
+-0.0006494705909348682 
+0.001192498722402708 
+0.0009823264434303319 
+0.001928384315523621 
+0.003321298828801261 
+0.002352426245908177 
+0.0002750006984774855 
+0.0004048130985910043 
+-0.001668246790787011 
+0.001487328276330092 
+3.340644152172541e-005 
+-0.0006988538453980235 
+0.00264404535862526 
+-0.001660398085138829 
+0.001830707808308397 
+0.001707907597965669 
+0.003509143347686815 
+0.002136807666747426 
+0.0001127921215547888 
+0.001778449039989992 
+0.0003973696779000191 
+0.001223403903598528 
+-0.0002294588193556762 
+-0.0002184399609493439 
+0.0006920375938489192 
+-0.0002500256845091261 
+-0.000426933979800025 
+-0.0001004139700393026 
+-0.000409703653132582 
+0.003234500956103735 
+-0.000812788996162925 
+-6.239979107910006e-006 
+0.0005413402173191207 
+0.0009978188814227889 
+0.001187401952379018 
+0.002112746705826906 
+-0.002260913324836196 
+-0.001659453243072217 
+0.003086822865290602 
+-0.001581208966550528 
+0.001488652810686538 
+-0.0005972177151875937 
+-0.003060917621038408 
+0.001678516450132472 
+0.001520473682417047 
+0.001966219375210702 
+0.004595608371439599 
+0.001112167083255031 
+-9.899911999344109e-005 
+0.002174569708327937 
+-0.003661835818578415 
+-0.002804552577730428 
+-0.002879254295678578 
+-0.0008441398389024955 
+0.00315331636923552 
+0.003615850604559958 
+0.0004613243528092508 
+0.001116053771147187 
+0.002200576109054272 
+0.002220246958632557 
+-0.0009247645924586413 
+-0.001922775901341873 
+0.001406722521090398 
+0.002428793714203375 
+-0.0008353874712068318 
+-0.000765826633412635 
+-0.001185196070313031 
+0.002850015203414008 
+0.00256890761460745 
+0.001880822576253037 
+-0.001899213785917481 
+0.002805623061585179 
+0.003114159111906259 
+0.0006472169493125273 
+-0.0003446358550056556 
+0.0008272012637238598 
+0.0009978911545506625 
+-0.001138749222009555 
+0.0007636149887827136 
+0.0003190758643446401 
+0.0001244951794580472 
+-0.0001661704251035895 
+-0.003042643153380162 
+-0.0008401456884493842 
+-0.001342690131929013 
+0.0009169104801507456 
+0.001457476730243217 
+-0.001926881283369534 
+-0.000149468967434895 
+0.001845092214945306 
+-0.0004686490302627312 
+-0.001128680894681623 
+0.0008298562417599503 
+0.00105275375656823 
+0.00147054344381228 
+0.003136255316251119 
+0.00424178433708677 
+-0.0003695684185233207 
+0.0009778018921549653 
+0.000318420215340312 
+0.0002846728342599034 
+-0.0008229653389717151 
+0.001408175836999388 
+0.002845839323728019 
+0.006462736319942868 
+0.003249841743223088 
+0.002799762352130509 
+0.000439042080545322 
+0.002813107986342101 
+0.001311817524740016 
+0.00122586330367399 
+0.001513688297838619 
+0.0005525807771752713 
+-1.700905723336665e-005 
+5.441696026381286e-005 
+-0.0001414460972361757 
+0.000916341540801566 
+0.0005352583670685076 
+0.0007106010474533635 
+0.001130596661481162 
+-0.001006597133651421 
+-0.002855871175137589 
+-0.001867137436433331 
+0.000816301041250733 
+0.0003027190036456308 
+0.002270333078722838 
+0.000995406272755508 
+1.613981070350419e-005 
+-0.0009468557835438064 
+0.001161892955551907 
+0.0004573778233833249 
+1.93262968704838e-005 
+0.0009773022261960612 
+0.001066436745473102 
+0.002364113684764118 
+0.002257806861870105 
+-0.001389923938325398 
+0.0003725237491809997 
+0.001366923038854325 
+0.002449589706455447 
+0.0009869620312033603 
+0.004199612004727671 
+-0.0006828913233250069 
+0.001106479658648222 
+0.0009909416119465474 
+0.002122718553267952 
+-0.0003478992610689801 
+0.001129713306707562 
+0.005108587768901567 
+0.0008194439196505427 
+0.0007371318512327206 
+0.0003371664777810032 
+0.002201593052201203 
+-0.0008453585370636733 
+-0.0009611849470325523 
+-0.000384563960647022 
+-0.001535733691341551 
+-0.0005517189744170037 
+0.002041478337671748 
+0.00017545812771416 
+0.001427326729579888 
+0.002633398561767754 
+0.001218103923455955 
+0.001578368127599233 
+0.001599476686811997 
+0.0003167213827787553 
+-0.001017126586960768 
+0.000474870757930076 
+0.00153278735917607 
+0.001313759878919915 
+0.001485771192940418 
+0.001927059415068355 
+0.00322338017259163 
+-0.0009333747801734334 
+0.003555708368586459 
+0.001596889536813054 
+-0.0003597639877869259 
+0.0007194534987191333 
+0.003511402109609577 
+0.001106971262134249 
+0.0001869910299758354 
+0.000290375015388559 
+0.001771799249627151 
+0.003644056110194333 
+0.001035557330613607 
+0.002442289572553691 
+-0.000265173207505303 
+-0.0005800179449936107 
+0.0009217647914449637 
+0.002967495968107593 
+8.907810416372393e-005 
+0.001311186887883266 
+0.0007279328923608641 
+0.001232292605398714 
+0.003764052704385186 
+0.001336748876896526 
+-0.002631455412016308 
+-0.0009138440525073828 
+-0.0001893983387710927 
+0.00390186171102783 
+0.0006733394075618671 
+-0.001611736413983418 
+-0.0002377240221160322 
+0.0001104415909618001 
+0.0003373702870130116 
+0.001641363040414891 
+0.001293867072043476 
+0.003402546708065364 
+-0.003153604432977936 
+0.0002569618842471533 
+0.001060463472635636 
+0.001213178830469504 
+0.001487565980486828 
+0.002066795871288383 
+0.002730248367241637 
+0.000603929474674968 
+-0.0007642228154860994 
+0.001781257021235545 
+-0.0004706349531334094 
+-0.0004030967895235289 
+0.001474485068375805 
+0.002019067926100776 
+-0.0001203068358159014 
+3.113492297295356e-006 
+0.0005408577830161899 
+-0.002785656378472691 
+0.0002962726734118604 
+-0.001047717405988731 
+-0.0001333763173020898 
+0.001659161696509777 
+0.003610414051081835 
+0.0008879823825875689 
+0.0002815136274828068 
+0.001119973769444101 
+0.002913166130347209 
+0.002860839540021754 
+0.003990593160649252 
+-0.001529954341662076 
+0.001320419407738797 
+-0.00082313609691137 
+0.002404947204027051 
+-0.0008949323033372203 
+0.002545021990982655 
+0.001717943986066685 
+-0.0006971610661187036 
+0.00231958091859971 
+0.0002881549375444366 
+-0.0002571561442136507 
+-0.001237560670968238 
+0.002900608225487241 
+-0.000817567024622426 
+-0.00142836478287216 
+9.782613697696893e-005 
+0.0003261681122797812 
+0.001326244579610851 
+0.0007387546584253009 
+0.001718506230548474 
+0.0006286257372368127 
+0.00114439311493381 
+0.0008396620161311858 
+-0.00159114148647417 
+-0.0009009673286398726 
+0.001407577268699247 
+5.2654386152383e-005 
+0.003482491935128033 
+0.001077348301113959 
+0.0002149289359256147 
+-0.001387975474957114 
+0.0007821847050728689 
+-0.002441586137908249 
+0.002598123366194804 
+0.0006448637102140111 
+0.0001765696055741777 
+-0.001631022567143885 
+0.001990202090286923 
+0.001908026233603102 
+-0.002301644870599717 
+0.003043661400240283 
+0.001213927492620288 
+0.0003141084324435197 
+-0.001461823687595186 
+0.002635949109900103 
+-0.00137489594507218 
+0.003578953996222509 
+0.0006301582775098219 
+0.003374988338920588 
+0.0002084301900889632 
+-4.46203279615068e-005 
+0.003927872156617354 
+-0.0001495578936843642 
+0.004609098813287749 
+0.002641972000103752 
+0.001647657077933135 
+0.002068809019682051 
+0.002207826882839669 
+0.0005596144540824485 
+-0.001658095692073935 
+-0.001212583344791502 
+0.0002878345468843371 
+0.002602349050812003 
+0.001498112157909103 
+0.0008833719301300267 
+-0.0006436878663416651 
+0.000455778536649397 
+0.003447737043958404 
+0.003577738958401979 
+-0.0008210432734321838 
+0.003614927634195696 
+-0.001547851316749247 
+0.0009359642289094413 
+-0.0007988042574346794 
+0.0007449697273710899 
+0.001883833693530887 
+0.0001802969251663417 
+0.002121059970563762 
+-0.0001132862869333302 
+-0.0005618620794531642 
+0.003441747608950622 
+0.003617281529240981 
+-0.001177960605165011 
+0.0003023161185411942 
+-0.001026912055477017 
+0.001869307715682101 
+0.001546314148411062 
+0.0005522624005197278 
+0.001388167710672025 
+0.001597524703909956 
+0.000842085321546492 
+-0.001417521969193216 
+0.001324994176607578 
+-0.001265523095765682 
+0.0006101200255231605 
+0.0001832403913341332 
+-0.0006017858887806263 
+0.000814425445264487 
+-0.0002196772832231774 
+0.001300659614279639 
+-0.000747409060098791 
+-0.0007388798299437707 
+-0.0008020728972800245 
+-0.001289936632975333 
+0.001250039895148947 
+0.0008183759401799029 
+-0.0006678630266648534 
+0.001796913842142573 
+-0.0003948077223593612 
+-0.001265065556269838 
+0.0007857429323402519 
+0.0009016603318566211 
+-0.002722400191801875 
+0.001615638661697688 
+0.0004603773224447304 
+0.0006326330401973011 
+-0.000234038540676119 
+0.000731902584100517 
+-1.879174318690593e-005 
+-0.001696420899731151 
+-0.001123970859133815 
+-0.0006006764873643408 
+0.0005396437633142235 
+-0.002354829495846894 
+-0.00132746451816014 
+-0.0003335198122750636 
+0.001559634284920335 
+-0.0003471563391654555 
+0.0008661511905751529 
+0.000695049291741742 
+4.122986413087891e-005 
+0.0008333840780250955 
+0.002835456803859915 
+0.001813436960228738 
+-0.002262467795384289 
+0.000619744222790096 
+-0.0007328362187294644 
+0.001633789996746061 
+0.0009778920091426209 
+0.001258745696581593 
+-0.0007327347404525504 
+0.001173134213463041 
+-0.0001120965993590384 
+0.002989666122326585 
+-0.0005279975740939165 
+-0.0006087307222369169 
+0.0006620533241124335 
+0.0002943800469024194 
+0.001523781238335323 
+0.0002512760366895166 
+-0.002945546857730055 
+0.0005809885168859898 
+0.002009325536232276 
+0.0006812939252709168 
+0.00282975568416363 
+0.005273403283199972 
+-0.001065267635344766 
+-0.0009976700167871264 
+3.505251838452074e-005 
+0.002908551030203454 
+0.0002276653453263907 
+0.002022350310928148 
+0.0008654192120557809 
+0.002236930742375254 
+0.0003504454590949298 
+0.0005388169376921593 
+0.0008968732955437291 
+-0.0004382557364141605 
+-0.0003996967866120859 
+-0.002633157194464933 
+-0.0004950629852018946 
+-0.000977768646069709 
+0.000776368090062961 
+0.001079788358460681 
+-5.702680875337225e-005 
+-0.002191887842995315 
+-0.002267797856464718 
+-0.001034547542649065 
+0.0005420916438367317 
+9.705263964854774e-005 
+-0.00349030818408077 
+0.001026453785278982 
+0.001722675963755837 
+-0.001282977760608197 
+0.0008505229512257552 
+0.0007166703136663667 
+-0.001582098441924648 
+0.0003044958186572839 
+4.40836697249732e-005 
+0.0006848956502451507 
+0.0007801723005713571 
+-0.003961863363100715 
+-0.001285851060364668 
+-0.0004372508306952774 
+-0.001750587528842246 
+0.003942220245924306 
+-0.0003728491852269179 
+0.0006240452696533366 
+0.0003931794140076768 
+0.002394318175666923 
+0.001160946820668282 
+7.097018767737788e-005 
+-0.0006640733346831446 
+0.00182246440086003 
+-0.000110747974127558 
+0.0009012373774781253 
+-0.001326364558862842 
+-0.0001745992991014805 
+0.003478675054436681 
+-0.0005390361452858429 
+-0.0006959826130726038 
+-0.0007660908392690618 
+-0.0006528798434912401 
+0.002298961154922542 
+0.001265744692409283 
+0.001260396246369192 
+0.00156885644066095 
+-0.00163467747663421 
+0.003126940592144163 
+0.001011787329373343 
+0.0007002112538259709 
+0.00154191046378319 
+0.00141926912822269 
+0.001064482615768491 
+0.0005974941737391755 
+-0.002396643457360635 
+7.298597805718118e-005 
+0.001766527473769153 
+0.001522347127329686 
+-0.000171610450632909 
+0.001181372460441368 
+0.00060408206622188 
+-0.0005844739694242455 
+0.001237758871730997 
+0.0002912250279830736 
+0.002554991122110226 
+-0.00278018718010625 
@@ -0,0 +1,506 @@
+solver_type L2R_L2LOSS_SVR_DUAL
+nr_class 2
+nr_feature 500
+bias 1
+w
+0.002605162206060179 
+-0.001472091965431503 
+0.001193909905203371 
+0.002144739338288731 
+-0.001749377558406725 
+0.001323436122699688 
+0.0003507390701459222 
+-7.846765362678149e-005 
+-0.003463208973392357 
+0.0004421144499594529 
+0.001833473111739364 
+0.0009508447766370538 
+0.002989971918963363 
+0.001191814765875848 
+-0.00265668426119822 
+0.001561476981010275 
+0.0002848676390002454 
+0.003285433517746234 
+0.000200699712007701 
+0.0006397172911964012 
+0.001405398966589253 
+0.0001959036500346391 
+0.001537527102436575 
+0.0007788006262410897 
+0.004019767494690636 
+-0.0024694510263496 
+0.003423289606299218 
+0.0008691782177177774 
+-1.494654736572215e-005 
+0.001525254422513723 
+0.003862836265029235 
+0.002125036172182977 
+0.003266205901900585 
+0.001357821321069907 
+0.001135728574558419 
+0.0006902912506074098 
+-0.000234971786451484 
+-0.0004180360196656417 
+5.023953580813245e-005 
+0.004326810129344937 
+-0.001883310704330575 
+0.0008255898976833249 
+-0.0009438205747517769 
+0.003288507826973241 
+0.002529936765433307 
+0.0010847424981391 
+-0.00205164848261108 
+-0.001584694079820821 
+0.0002626000924347976 
+0.0006575087586658033 
+-9.681664391317167e-005 
+-0.0002084149741719356 
+-0.002341690606435181 
+0.001129677775070529 
+0.002612596493676696 
+0.0002781724734924659 
+0.0007018836048131403 
+-0.0006693293687038051 
+-0.001689164528106299 
+0.0001413106960752519 
+-0.0003423310604756451 
+0.0003705327339805738 
+-0.002490794511524049 
+-0.001162928283000122 
+-0.001040245132462882 
+0.0002407578728641261 
+0.0003875816913937285 
+0.0002484622104781383 
+0.0009213824589765286 
+-0.00230355720975048 
+0.002064485817309516 
+0.001028050271170841 
+0.002098180124121605 
+0.001640539955161992 
+0.001119459477564629 
+0.001253363079674738 
+-0.0004769869605310309 
+-0.001666160029720203 
+-0.001182598366599691 
+0.0009072080644154841 
+-0.001329412492817096 
+0.004444539370503616 
+0.001849727135507289 
+-0.001166981838479384 
+0.000791091791797372 
+0.002032091724762388 
+0.002830826400909323 
+-0.0003792990162779232 
+-0.003479875127943903 
+-0.0005350900717210162 
+0.002043201654662796 
+0.0001965893582635767 
+-0.0001371238824561785 
+-0.0008106382210100625 
+0.00148435241086275 
+-0.0009440209251834071 
+0.002862802827119041 
+-0.001135645892834673 
+-0.00120237267417065 
+-0.001949857285761335 
+-0.0001382100004043848 
+0.0008609710233836159 
+8.152100595777721e-005 
+9.805102882013882e-005 
+-0.002266413982942071 
+-0.001062986924594547 
+-8.899800980990754e-005 
+0.001314967619101446 
+-0.0009440986513884611 
+5.731579824522643e-005 
+-0.0006809542091505442 
+-0.001817191194984125 
+-0.000815324093139249 
+0.002187084536499781 
+-0.003104183103466754 
+-0.000345494388935753 
+0.001296356189059482 
+0.001332288495174361 
+-0.004059341146642911 
+-0.0006601083065536066 
+-0.0007414283141487853 
+-0.001588524020555137 
+0.0006505036490025935 
+0.001801677937673249 
+-0.001332010374081228 
+0.00334872919055607 
+0.001171378045175447 
+0.001327206544745418 
+-0.0008719507427481622 
+-0.001574815325125707 
+0.003045479088411038 
+0.005625040976034036 
+0.0003761425526094415 
+0.0006416507983289115 
+0.00297611723465161 
+0.001831797407817577 
+-0.001786270955094395 
+-0.001904188321943547 
+-0.0002729988479236507 
+0.002467158817714775 
+-0.0002538585743375627 
+-1.322889416268927e-005 
+0.002320125764725968 
+-0.001825737842011375 
+-0.0004659617758831124 
+0.003638263609047125 
+0.001716028885044811 
+0.003009364430980831 
+0.0007368110088194897 
+-0.001032640776866736 
+-0.0005314521713460505 
+-0.002073444587547883 
+0.001287748355306162 
+-0.0004840814687198754 
+0.0009138720750723853 
+-0.001928246813570929 
+0.002651690972638656 
+-7.547095061616201e-005 
+0.0029178714436312 
+0.002688902856128762 
+-0.0006675496327761262 
+0.002774992255550119 
+0.0004055250796016525 
+-0.0024342404107424 
+-8.37081284493154e-005 
+0.001424348968798708 
+0.001813007892809583 
+-7.622664319043213e-005 
+0.0008773208214135538 
+-0.000840643242220864 
+0.001177267907741954 
+-0.001273888517566433 
+0.0007652225428271607 
+0.002426791638008896 
+-0.001509641635589666 
+0.004345171495561568 
+-0.001131326905201481 
+-6.744896765516797e-005 
+-0.0003594633364584458 
+0.0005346180716076258 
+-0.001628418447709459 
+0.0006598187483046005 
+0.0007358552159980505 
+0.0004967276222277877 
+-0.000763093376100163 
+0.0005306054443928539 
+-0.001472570874400998 
+0.001046256597005959 
+0.002483566882364665 
+-0.0009854097900840575 
+0.0006824979958834789 
+-0.0003784313169985191 
+0.0009843429438696736 
+-0.0002816711580461689 
+-0.0006351561192819331 
+0.001598790158404059 
+0.002260165671630609 
+0.0006400771093172772 
+-0.0009409650536458136 
+0.003777982475225834 
+-0.0007860136282481651 
+0.002970336618985869 
+0.0005406346857829075 
+0.0007885133168467327 
+0.001524677783131273 
+0.003945597129092131 
+0.003275855156501855 
+0.0005793337601484919 
+-0.002052637506585683 
+-0.0005796744964655264 
+0.004668184590756228 
+0.001456920117274799 
+-0.001829203892720271 
+0.001750949964497285 
+-0.0001181639345420844 
+0.0008476211950812182 
+0.000303389423924617 
+-0.0002720875621791807 
+-0.001345350867740706 
+0.001392826794368624 
+0.003365762953674832 
+0.002141111795051495 
+0.0001684079693459364 
+0.002049852372826755 
+0.001933734837462584 
+0.001620103548819295 
+0.003848836436884468 
+-0.0006519348008070052 
+-0.0008651359574649852 
+4.121268765844798e-005 
+-0.0002948217230016978 
+-0.001210918081437684 
+0.0003932962052382394 
+0.002421309547640413 
+-0.0004663403454421675 
+-0.002173833256569554 
+0.003214893791300685 
+-0.0008369814489583905 
+-0.0003184643436498925 
+-0.001683022221859073 
+0.0008046068199111757 
+0.001316750672489298 
+-5.496886272042534e-005 
+-0.002782045576354208 
+-0.0008814255744881731 
+0.001796209779397872 
+0.001700762150430318 
+0.001881251979906568 
+0.0006794150769523206 
+6.21999975467151e-005 
+-0.001561335966700881 
+-1.821342467499658e-006 
+-0.0008574249901958335 
+-0.0006696151244284204 
+-0.002201447731534094 
+-0.002307732582258395 
+-0.001315746720452059 
+0.002824972803616357 
+-0.001009688983533697 
+0.0002347155036940288 
+0.0005558512296471466 
+0.002293225898223852 
+0.001091322555215698 
+0.004713499560288406 
+-0.002212353868797088 
+0.00170030981595098 
+0.0007555921385385295 
+-0.000885708472852782 
+-0.001772538919836531 
+0.002387999395252449 
+0.001790139262154665 
+-0.004658628275747407 
+0.0006075521482066035 
+-0.001497968271097847 
+-0.0002533123945563971 
+0.0007118040262430449 
+0.0001932333089999665 
+-0.001600361587903945 
+0.0002855075920941781 
+0.00124128542792171 
+0.001385506144084131 
+-0.0001398554814062079 
+0.001075767067962076 
+0.0007143914631058003 
+-0.0004806289688545247 
+-0.00173019176353133 
+0.000212441252338061 
+0.000703257668474831 
+0.0001097189373243031 
+-1.720603979063054e-005 
+-0.001082597647150342 
+0.003370572907980223 
+-0.0005378091352165564 
+0.000656800149605375 
+-0.000532684839681119 
+0.0001538438853471965 
+0.001445185884839459 
+0.001669077211490679 
+-0.001130420612381501 
+0.0009064127367975756 
+-0.0003024065417510699 
+-0.0004326678727770649 
+0.002473090125026581 
+-0.001013881107054315 
+0.001174999183423075 
+0.00174940157261738 
+0.002129005740492941 
+0.001744246737810397 
+0.001555610296947044 
+-0.001868030423044575 
+0.001694667628994438 
+0.001180941948212399 
+-0.0003384463247659496 
+0.000156611315496443 
+0.001986207751783147 
+0.005724136538637812 
+-0.001014342645068951 
+0.004161541066055778 
+-0.000789083537791291 
+-0.0003337970619524984 
+0.002809452323759541 
+0.002722443682275564 
+0.0005439710160439719 
+-0.0004279153691394782 
+0.0007526732280038493 
+-6.143559351224582e-005 
+-0.002196481757826111 
+-0.001954303669661267 
+0.0002716038053974922 
+0.001730703089617006 
+-0.0009780691126774598 
+0.001687142507490198 
+0.003808628178377112 
+0.000839648646186886 
+0.002615495964182224 
+-0.002863840283493402 
+-0.0002000123161701871 
+-0.0008046993134804906 
+0.000667158004618861 
+0.0003372262195252452 
+0.0002732416043761785 
+-0.002471328948211941 
+0.0001566901680276102 
+0.0004807036977722124 
+0.001400958800622671 
+0.00187715296378951 
+-0.0006001379706036187 
+0.0005973651138337257 
+0.001431407212801983 
+0.005327920892087485 
+-0.001633950236274221 
+-0.001938822525749577 
+-0.0007775313827548838 
+-0.001261409740557187 
+-0.0003948479478055902 
+-0.0003172428080099547 
+0.002263911924278274 
+0.0005068955464824282 
+0.002677603529554166 
+-0.002346514676768802 
+-0.001566809835778487 
+0.002535247195684115 
+-0.001449720990948347 
+0.002329225885083865 
+0.0004210446112108766 
+0.001499202581277419 
+-2.783888294125558e-005 
+-0.001811360689235398 
+-0.002704587799854568 
+-0.0008706770793824335 
+-0.001230965191611267 
+0.003031620013968557 
+-0.002391887195278595 
+-9.267269432091334e-005 
+0.000266853800769517 
+-0.0002286990163569764 
+0.0003773100408423015 
+-0.002615899448396195 
+0.001385337504644116 
+-0.001446722088664313 
+-0.001025023595899365 
+0.002273844381815133 
+-3.114252921102228e-005 
+-0.0005625438034246383 
+3.094849939184497e-005 
+0.0003912642047494195 
+0.002620015796863886 
+-0.001018203271337412 
+-0.001478280756628229 
+-0.0004230630581522384 
+-0.0004310539013829823 
+-0.00185877714070625 
+-0.0003469331383689908 
+0.002222061675546858 
+-0.0005135782125866714 
+0.004598128080857131 
+0.003233801657658935 
+0.004009695722682436 
+-0.001208420198633167 
+0.002067307497117762 
+0.002663896421150825 
+0.001958675117946425 
+-0.002643414340374418 
+0.0006064300529885675 
+1.739230188498241e-006 
+0.0004822555347317731 
+0.001066209039809392 
+0.002976340324013392 
+0.0002502610850205078 
+0.000728311570772182 
+0.0007126759536257385 
+-0.002262457534091425 
+0.0002886236984353326 
+-0.0006295121779181293 
+-0.0003722022929604411 
+0.002243069264750704 
+0.001299602027892652 
+-0.001855357867440572 
+0.0005140216292871075 
+0.002597882458883753 
+0.001162640062537186 
+0.0009422160445958062 
+0.001201029044525468 
+0.0033363117673962 
+0.0004951899354902913 
+0.00228602753051162 
+0.001865615876320911 
+0.0006335097744041983 
+0.004461412518401789 
+-0.0002958989907655057 
+0.001157244109442636 
+-0.003842450386495464 
+-0.001467104902561963 
+-0.002291058674424038 
+-0.001359546106812545 
+0.001633860097881385 
+0.001745602448261993 
+-0.001306708184247726 
+-0.0006292925183246526 
+-7.068866564059419e-006 
+-0.002548109822781161 
+0.001766399057308826 
+0.0002128448078300415 
+-0.001432722745251132 
+-0.001088339188646447 
+0.001954150425853544 
+0.0009054532444743234 
+0.001435038886746492 
+0.0007112506803623181 
+0.001107023580637897 
+-0.001924038608685806 
+0.0003014170380030285 
+1.817255344604322e-005 
+0.0008269866626449576 
+0.001637923980242403 
+-0.002310707664954007 
+0.0004438102202628633 
+0.002514910837368378 
+-0.0005432659105068842 
+0.001446467735554032 
+-0.00246814684271538 
+0.0002209281186630151 
+-0.003155142374028704 
+-0.0006220638926040524 
+0.0030603762417604 
+0.0009688040426069092 
+-0.002012639088856971 
+-0.001641430794295916 
+-0.001860534122687048 
+0.001196433762286324 
+-0.001837430041241428 
+0.0008270955577951972 
+-0.001169602750806934 
+2.65085828195483e-005 
+0.001544438578499803 
+-7.983352584739467e-005 
+0.001036019595442713 
+0.0007561391702774874 
+0.001520169850175026 
+-0.002014239832054699 
+-0.001736088688724359 
+-0.001555710749651749 
+-0.001665361197165054 
+-0.001637702157491784 
+0.001631153232914698 
+0.004049874047225024 
+-0.001228103760345923 
+0.0009491789809335045 
+0.0002406497679497205 
+0.001434977456407217 
+0.001335371072491472 
+0.001797888643218709 
+-0.0006044168083831356 
+-0.004902074316991959 
+0.003976502020241338 
+0.0001355233348498881 
+-0.0008970680310158709 
+0.000128434762944971 
+0.00030107007872832 
+0.0007412019150243649 
+0.03234364097191275 
@@ -0,0 +1,18 @@
+help:OpenXBOW Generates an ARFF or CSV file (separator: semicolon) from an ARFF or CSV file of features (numeric and/or textual) over time.\n\n\
+Input format:\n\
+The first feature must always be an identifier for the corresponding wave file / instance / analysis window, i.e. string containing the filename or an index, e.g. 'corpus_001.wav'.\n\
+A header line in CSV files is mandatory if there are only text features and labels, otherwise it is optional.\n\
+The last feature may be a nominal or numeric class label. In this case, there must be a header line.\n\
+If the class labels are not given in the input data file, an additional CSV file with class labels can be given (the first line must be a header line, the first column contains the identifier string for each instance, the second column the corresponding class label.\n\n\
+Example for an input CSV file:\n\
+'corpus_0001.wav';1.04E+01;2.3E+00;2.7E-01;classA\n\
+'corpus_0001.wav';9.02E+00;7.0E+01;1.1E-01;classA\n\
+'corpus_0001.wav';5.19E+01;4.4E+00;2.7E-01;classA\n\
+'corpus_0002.wav';1.24E+00;1.3E+01;2.8E-01;classB\n\
+'corpus_0002.wav';2.51E+01;6.7E+00;3.1E-01;classB\n\
+'corpus_0002.wav';4.24E+01;2.2E+01;8.0E-02;classB\n\
+'corpus_0003.wav';1.23E+01;4.3E+00;1.6E-01;classA\n\
+...
+
+example:Example:\n\
+java -jar openXBOW.jar -i features.arff -o boaw.arff -l labels.csv -size 100
@@ -0,0 +1,74 @@
+h:Print this help\n
+
+# IO
+i:Name/Path of an input (ARFF or CSV) file p containing feature vectors over time\n\
+  The first feature must be a string or number which specifies all feature vectors which belong to one analysis window/instance.
+attributes:An optional string, specifying all input attributes (mandatory if multiple label): \n\
+           n=name, t=time stamp, 0=text feature, [1-9]=numeric feature, c=class label/numeric label, r=remove attribute\n\
+           Using different numbers for numeric features will create a separate codebook and bag for all features belonging to the same index.
+o:Name / Path of an output ARFF, CSV or LibSVM file p containing the bag-of-features representation.\n\
+  The file format depends on the given file ending (*.arff, *.csv or *.libsvm).
+writeName:Output the id string/number in the output file (only ARFF & CSV).
+writeTimeStamp:Output the time stamp in the output file (only ARFF & CSV).
+l:CSV file p with the class labels for each analysis window/instance.\n\
+  Both nominal and numeric classes are supported. Format:\n\
+  1st line: name (according to the input file); label1; label2; ...\n\
+  2nd line: 'file_1.wav'; class1; ...\n\
+            [and so on]\n
+
+# Preprocessing options
+t:Segment the input files with a windows size (segment width) of p1 seconds and a hop size (shift) of p2 seconds\n\
+  If this option is used, the second column of the input file must be a time index (in seconds) of the current frame and \n\
+  the (optional) labels file must have three columns (name; time; label). The time instances where labels are given must \n\
+  fit with the given parameters.\n
+e:Remove all feature vectors from the input, where the activity (or energy) is below p2. Index p1 specifies the index of the activity feature - starting with 1.
+standardizeInput:Standardize all numeric input features.\n\
+  The parameters are stored in the codebook file (-B) and then used for standardization of test data (-b) in an online approach.
+normalizeInput:Normalize all numeric input features (min->max is normalized to 0->1).\n\
+  The parameters are stored in the codebook file (-B) and then used for standardization of test data (-b) in an online approach.
+
+# Codebook (only numeric features)
+size:Set the (initial) size p of the codebook. (default: size=500)
+c:Method of creating the codebook:\n\
+  p=random (default): Generate the codebook by random sampling of the input feature vectors.\n\
+  p=random++: Generate the codebook by random sampling of the input feature vectors with weighting similiar to initialization of kmeans++.\n\
+  p=kmeans: Employ kmeans clustering (Lloyd's algorithm).\n\
+  p=kmeans++: Employ kmeans++ clustering (Lloyd's algorithm).
+reduce:Reduce the size of the codebook by merging words which are correlated with each other. PCC with threshold p is considered.
+supervised:Generate a codebook for each class separately, first, then merge all codebooks. (Not available for numeric labels.)
+seed:Select the random seed p used for codebook creation. (Has no effect on training selection configured by -numTrain).
+numTrain:Randomly choose p feature vectors from the input data for the creation of the codebook (should not be used for random sampling).
+svq:If >= 1, split vector quantization (SVQ) is used. The feature vectors are split into p1 sub-vectors. Codebooks are created for each sub-vector.\n\
+  Then, a final codebook and bag is created from the assigned indexes of the sub-vectors. p2 specifies the size of the sub-codebooks.\n
+
+b:Load codebook p (do not create one).
+B:Save the created codebook as a file p.\n
+
+# Assignment (only numeric)
+a:When creating the bag-of-features, assign each feature vector p vectors from the quantized vectors in the codebook. (default: a=1)
+gaussian:Soft assignment using Gaussian encoding with standard deviation p.\n
+
+# Assignment (only text)
+minTermFreq:Gives a minimum threshold for the number of occurrences of each word/n-gram to be considered for codebook generation (default: minTermFreq=1)
+maxTermFreq:Gives a maximum threshold for the number of occurrences of each word/n-gram to be considered for codebook generation (default: minTermFreq=0(inf))
+stopChar:Specifies characters which are removed from all input instances (default: .,;:()?!* )
+nGram:N-gram (default: nGram=1)
+nCharGram:N-character-gram (default: nCharGram=0)\n
+
+# Assignment general
+log:Logarithmic term weighting 'lg(TF+1)' of the term frequency.\n\
+    This parameter is transmitted in the codebook file. If a codebook is loaded the term weighting specified therein is taken.
+idf:Inverse document frequency transform: Multiply the term frequency (TF) with the logarithm of the ratio of the \n\
+    total number of instances and the number of instances where the respective word is present.\n\
+    This parameter and the idf weights are transmitted in the codebook file.\n\
+    If a codebook is loaded the term weighting specified therein is taken.
+norm:Normalize the bag-of-features (3 options of normalization).\n\
+     p=1: Divides the term frequencies (TF) by the number of input frames.\n\
+     p=2: Divides the TF by the sum of all TFs.\n\
+     p=3: Divides the TF by a factor so that the resulting Euclidean length is 1.\n
+
+# Postprocessing options
+standardizeOutput:Standardize all output features (term frequencies).\n\
+  The parameters are stored in the codebook file (-B) and then used for standardization of test data (-b) in an online approach.
+normalizeOutput:Normalize all output features (term frequencies, min->max is normalized to 0->1).\n\
+  The parameters are stored in the codebook file (-B) and then used for standardization of test data (-b) in an online approach.
@@ -0,0 +1,32 @@
+#!/bin/bash
+# Arousal and valence prediction using bag-of-audio-words
+
+wavfile=$1 #'/media/sag/DATA/workPassau/Projects/MixedEmotions/Databases/Youtube_data_package/data/Audio/video1(00h00m27s-00h01m01s).wav'
+interval=0.04     # hop size
+
+#./SMILExtract -C "mfcc_energy.conf" -logfile "smile.log" -I $wavfile -instname $wavfile -csvoutput "LLD.csv" -l 1
+#./SMILExtract -C "mfcc_energy.conf" -logfile "smile.log" -I $wavfile -instname $wavfile -csvoutput "LLDval.csv" -l 1
+
+#java -jar openWord.jar -i LLDval.csv -o boaw.libsvm -a 20 -size 1000 -t 10.0 $interval -b bookValence &>/dev/null
+#./predict boaw.libsvm modelValence.svr valence.txt &>/dev/null
+NEW_UUID='LLD'$(date | md5sum | awk '{ print substr( $0, 1, 10 ) }')'a'
+./SMILExtract -C "mfcc_energy.conf" -logfile "smile.log" -I $wavfile -instname $wavfile -csvoutput ${NEW_UUID}.csv -l 1
+
+java -jar openXBOW.jar -i ${NEW_UUID}.csv -attributes nt1111111111111 -o boaw.libsvm -a 10 -norm 1 -b book &>/dev/null
+./predict boaw.libsvm modelArousal.svr ${NEW_UUID}arousal.txt &>/dev/null
+#cat valence.txt | awk '{ sum += $1; sum2+=$1*$1; n++ } END { if (n > 0) print sum/n , 1-((sum2/n)-(sum/n*sum/n))^.5; }' > Vres.txt
+
+input=${NEW_UUID}arousal.txt
+
+i=1
+while read mean 
+do
+#  if [[ $std == *"nan"* ]]
+#  then
+#    std=1;
+#  fi
+a=`awk "BEGIN{printf \"%.3f\",$mean}"`
+printf '{ "PROCESSOR":"OpenSMILE","ORIGIN":"boaw","TYPE":"regression","COMPONENT":"maxboaw2","VIDX":'$i',"VALUE":'$a',"PROB":[{"CONFIDENCE":1}]}\n'
+done < "$input"
+
+rm ${NEW_UUID}arousal.txt ${NEW_UUID}.csv
@@ -0,0 +1,32 @@
+#!/bin/bash
+# Arousal and valence prediction using bag-of-audio-words
+
+wavfile=$1 #'/media/sag/DATA/workPassau/Projects/MixedEmotions/Databases/Youtube_data_package/data/Audio/video1(00h00m27s-00h01m01s).wav'
+interval=0.04     # hop size
+
+#./SMILExtract -C "mfcc_energy.conf" -logfile "smile.log" -I $wavfile -instname $wavfile -csvoutput "LLD.csv" -l 1
+#./SMILExtract -C "mfcc_energy.conf" -logfile "smile.log" -I $wavfile -instname $wavfile -csvoutput "LLDval.csv" -l 1
+
+#java -jar openWord.jar -i LLDval.csv -o boaw.libsvm -a 20 -size 1000 -t 10.0 $interval -b bookValence &>/dev/null
+#./predict boaw.libsvm modelValence.svr valence.txt &>/dev/null
+NEW_UUID='LLD'$(date | md5sum | awk '{ print substr( $0, 1, 10 ) }')'a'
+./SMILExtract -C "mfcc_energy.conf" -logfile "smile.log" -I $wavfile -instname $wavfile -csvoutput ${NEW_UUID}.csv -l 1
+
+java -jar openXBOW.jar -i ${NEW_UUID}.csv -attributes nt1111111111111 -o boaw.libsvm -a 10 -norm 1 -b book &>/dev/null
+./predict boaw.libsvm modelArousal.svr ${NEW_UUID}arousal.txt &>/dev/null
+#cat valence.txt | awk '{ sum += $1; sum2+=$1*$1; n++ } END { if (n > 0) print sum/n , 1-((sum2/n)-(sum/n*sum/n))^.5; }' > Vres.txt
+
+input=${NEW_UUID}arousal.txt
+
+i=1
+while read mean 
+do
+#  if [[ $std == *"nan"* ]]
+#  then
+#    std=1;
+#  fi
+a=`awk "BEGIN{printf \"%.2f\",$mean}"`
+printf '{ "PROCESSOR":"OpenSMILE","ORIGIN":"boaw","TYPE":"regression","COMPONENT":"maxboaw2","VIDX":'$i',"VALUE":'$a',"PROB":[{"CONFIDENCE":1}]}\n'
+done < "$input"
+
+rm ${NEW_UUID}arousal.txt ${NEW_UUID}.csv
@@ -0,0 +1,32 @@
+#!/bin/bash
+# Arousal and valence prediction using bag-of-audio-words
+
+wavfile=$1 #'/media/sag/DATA/workPassau/Projects/MixedEmotions/Databases/Youtube_data_package/data/Audio/video1(00h00m27s-00h01m01s).wav'
+interval=0.04     # hop size
+
+#./SMILExtract -C "mfcc_energy.conf" -logfile "smile.log" -I $wavfile -instname $wavfile -csvoutput "LLD.csv" -l 1
+#./SMILExtract -C "mfcc_energy.conf" -logfile "smile.log" -I $wavfile -instname $wavfile -csvoutput "LLDval.csv" -l 1
+
+#java -jar openWord.jar -i LLDval.csv -o boaw.libsvm -a 20 -size 1000 -t 10.0 $interval -b bookValence &>/dev/null
+#./predict boaw.libsvm modelValence.svr valence.txt &>/dev/null
+NEW_UUID='LLD'$(date | md5sum | awk '{ print substr( $0, 1, 10 ) }')'a'
+./SMILExtract -C "mfcc_energy.conf" -logfile "smile.log" -I $wavfile -instname $wavfile -csvoutput ${NEW_UUID}.csv -l 1
+
+java -jar openXBOW.jar -i ${NEW_UUID}.csv -attributes nt1111111111111 -o boaw.libsvm -a 10 -norm 1 -b book &>/dev/null
+./predict boaw.libsvm modelValence.svr ${NEW_UUID}valence.txt &>/dev/null
+#cat valence.txt | awk '{ sum += $1; sum2+=$1*$1; n++ } END { if (n > 0) print sum/n , 1-((sum2/n)-(sum/n*sum/n))^.5; }' > Vres.txt
+
+input=${NEW_UUID}valence.txt
+
+i=1
+while read mean 
+do
+#  if [[ $std == *"nan"* ]]
+#  then
+#    std=1;
+#  fi
+a=`awk "BEGIN{printf \"%.3f\",$mean}"`
+printf '{ "PROCESSOR":"OpenSMILE","ORIGIN":"boaw","TYPE":"regression","COMPONENT":"maxboaw2","VIDX":'$i',"VALUE":'$a',"PROB":[{"CONFIDENCE":1}]}\n'
+done < "$input"
+
+rm ${NEW_UUID}valence.txt ${NEW_UUID}.csv
@@ -0,0 +1,32 @@
+#!/bin/bash
+# Arousal and valence prediction using bag-of-audio-words
+
+wavfile=$1 #'/media/sag/DATA/workPassau/Projects/MixedEmotions/Databases/Youtube_data_package/data/Audio/video1(00h00m27s-00h01m01s).wav'
+interval=0.04     # hop size
+
+#./SMILExtract -C "mfcc_energy.conf" -logfile "smile.log" -I $wavfile -instname $wavfile -csvoutput "LLD.csv" -l 1
+#./SMILExtract -C "mfcc_energy.conf" -logfile "smile.log" -I $wavfile -instname $wavfile -csvoutput "LLDval.csv" -l 1
+
+#java -jar openWord.jar -i LLDval.csv -o boaw.libsvm -a 20 -size 1000 -t 10.0 $interval -b bookValence &>/dev/null
+#./predict boaw.libsvm modelValence.svr valence.txt &>/dev/null
+NEW_UUID='LLD'$(date | md5sum | awk '{ print substr( $0, 1, 10 ) }')'a'
+./SMILExtract -C "mfcc_energy.conf" -logfile "smile.log" -I $wavfile -instname $wavfile -csvoutput ${NEW_UUID}.csv -l 1
+
+java -jar openXBOW.jar -i ${NEW_UUID}.csv -attributes nt1111111111111 -o boaw.libsvm -a 10 -norm 1 -b book &>/dev/null
+./predict boaw.libsvm modelValence.svr ${NEW_UUID}valence.txt &>/dev/null
+#cat valence.txt | awk '{ sum += $1; sum2+=$1*$1; n++ } END { if (n > 0) print sum/n , 1-((sum2/n)-(sum/n*sum/n))^.5; }' > Vres.txt
+
+input=${NEW_UUID}valence.txt
+
+i=1
+while read mean 
+do
+#  if [[ $std == *"nan"* ]]
+#  then
+#    std=1;
+#  fi
+a=`awk "BEGIN{printf \"%.3f\",$mean}"`
+printf '{ "PROCESSOR":"OpenSMILE","ORIGIN":"boaw","TYPE":"regression","COMPONENT":"maxboaw2","VIDX":'$i',"VALUE":'$mean',"PROB":[{"CONFIDENCE":1}]}\n'
+done < "$input"
+
+rm ${NEW_UUID}valence.txt ${NEW_UUID}.csv
@@ -0,0 +1,64 @@
+{
+"configs":[
+{
+	"id":"arousal",
+	"classifier":"bash",	
+	"intype":"audio",
+	"run_command":"boaw_models/run_ars.sh",
+	"onyxentity":"emovoc:arousal"
+},{
+	"id":"valence",
+	"classifier":"bash",	
+	"intype":"audio",
+	"run_command":"boaw_models/run_val.sh",
+	"onyxentity":"emovoc:valence"
+},{
+	"id":"gender",
+	"classifier":"bash",	
+	"intype":"audio",
+	"run_command":"RF_models/run_gender.sh",
+	"onyxentity":"gender"
+},{
+	"id":"age",
+	"classifier":"bash",	
+	"intype":"audio",
+	"run_command":"RF_models/run_age.sh",
+	"onyxentity":"age"
+},{
+	"id":"big5a",
+	"classifier":"bash",	
+	"intype":"audio",
+	"run_command":"RF_models/run_Agreeable.sh",
+	"onyxentity":"Agreeableness"
+},{
+	"id":"big5c",
+	"classifier":"bash",	
+	"intype":"audio",
+	"run_command":"RF_models/run_Concious.sh",
+	"onyxentity":"Concioustiousness"
+},{
+	"id":"big5o",
+	"classifier":"bash",	
+	"intype":"audio",
+	"run_command":"RF_models/run_Openness.sh",
+	"onyxentity":"Openness"
+},{
+	"id":"big5e",
+	"classifier":"bash",	
+	"intype":"audio",
+	"run_command":"RF_models/run_Extroversion.sh",
+	"onyxentity":"Extroversion"
+},{
+	"id":"big5n",
+	"classifier":"bash",	
+	"intype":"audio",
+	"run_command":"RF_models/run_Neuroticism.sh",
+	"onyxentity":"Neuroticism"
+},{
+	"id":"sentiment",
+	"classifier":"bash",	
+	"intype":"text",
+	"run_command":"sentiment/sentiment_runner.sh",
+	"onyxentity":"Sentiment"
+}
+]}
@@ -0,0 +1,2 @@
+#!/bin/bash
+sudo pip install pandas numpy tensorflow  cPickle re os
@@ -0,0 +1,2 @@
+#!/bin/bash
+sudo pip install pandas
@@ -0,0 +1,392 @@
+import numpy as np, pandas as pd, os, re, string, cPickle, tensorflow as tf
+from random import shuffle
+
+from itertools import izip_longest
+
+np.random.seed(123)
+
+a = None
+
+FLAGS = tf.app.flags.FLAGS
+tf.app.flags.DEFINE_string('mode', 'train', """train or evaluate.""")
+tf.app.flags.DEFINE_string('sentence', '', '')
+
+
+def create_word_vecs(sentences, lower=True, min_freq=4):
+    """ Creates word vectors using a corpus of sentences.
+    ATTENTION: Always remember to create word vectors from the training set
+        ONLY. Never use the dev or test sets to create word vectors.
+
+    Creates a numpy ndarray with ndim=2, where each line is a word vector from
+        a word in a corpus. Each vector is initialized by drawing from a
+        gaussian distribution with mean 0 and std 0.1
+
+    This function also creates word vectors for the tokens `MASK` and `UNK`,
+        for masking indexes and unknown words, respectively.
+
+    :param sentences: List of list of strings, i.e. a list of tokenized
+        sentences.
+    :param lower: If the words should be converted to their lower case
+        counterpart. Default=True
+    :param min_freq: The minimum number of occurrences that a word should have
+        for a word vector to be created. Default=4
+
+    :returns: A tuple, where the first element is a numpy matrix with each word
+        vector created and the second element is a `word2index` dict. This dict
+        is indexed by the words and returns their index in the word vectos
+        matrix.
+    """
+    words = {}
+
+    for sentence in sentences:
+        for word in sentence:
+            if lower:
+                word = word.lower()
+            if word not in words:
+                words[word] = 0
+            words[word] += 1
+
+    words_to_use = []
+    for word, count in words.items():
+        if count < min_freq:
+            continue
+        words_to_use.append(word)
+
+    words = words_to_use
+
+    word_vecs = np.random.normal(loc=0.0, scale=.1, size=(len(words) + 2, 30))
+    word2index = {}
+    word2index['MASK'] = 0 #For Keras masking
+    word2index['UNK'] = 1 #Out of vocabulary words
+
+    for word in words:
+        word2index[word] = len(word2index)
+
+    return word_vecs.astype('float32'), word2index
+
+def encode_sentences(sentences, word2index):
+    """ Encodes all sentences in a tokenized corpus using a word2index dict.
+
+    :param sentences: List of list of strings, i.e. a list of tokenized
+        sentences.
+    :param word2index: Dict with tokens as keys and indexes as values
+
+    :returns: List of list of ints, i.e. the translated corpus
+    """
+    translated = []
+
+    for sentence in sentences:
+        translated_sentence = []
+        for word in sentence:
+            word = word.lower()
+            if word not in word2index:
+                word = 'UNK'
+            translated_sentence.append(word2index[word])
+        translated.append(translated_sentence)
+    return translated
+
+
+def to_np_ndarray(data):
+    """ Takes an encoded corpus and transforms it into a numpy ndarray, padding
+        if necessary
+    """
+
+    def find_shape(seq):
+        try:
+            len_ = len(seq)
+        except TypeError:
+            return ()
+        shapes = [find_shape(subseq) for subseq in seq]
+        return (len_,) + tuple(max(sizes) for sizes in izip_longest(*shapes,
+                                                                    fillvalue=1))
+
+    def fill_array(arr, seq, val=0):
+        if arr.ndim == 1:
+            try:
+                len_ = len(seq)
+            except TypeError:
+                len_ = 0
+            arr[:len_] = seq
+            arr[len_:] = val
+        else:
+            for subarr, subseq in izip_longest(arr, seq, fillvalue=()):
+                fill_array(subarr, subseq)
+
+    padded_data = np.empty(shape=find_shape(data))
+    fill_array(padded_data, data)
+
+    return padded_data.astype('int32')
+
+def encode_labels(data):
+    """ Takes a list of strings (labels) and builds a matrix of one-hot vectors
+            and a label2index dict
+    """
+    label2index = {}
+    encoded_labels = []
+    for label in data:
+        if label not in label2index:
+            label2index[label] = len(label2index)
+        encoded_labels.append(label2index[label])
+
+    onehot_labels = np.zeros(shape=(len(data), len(label2index)), dtype='int32')
+    onehot_labels[np.arange(len(data)), encoded_labels] = 1
+
+    return onehot_labels, label2index
+
+def clean_tweet(tweet):
+    #Convert to lower case
+    tweet = tweet.lower()
+    #Convert www.* or https?://* to URL
+    tweet = re.sub('((www\.[^\s]+)|(https?://[^\s]+))','URL',tweet)
+    #Convert @username to AT_USER
+    tweet = re.sub('@[^\s]+','ATUSER',tweet)
+    #Remove additional white spaces
+    tweet = re.sub('[\s]+', ' ', tweet)
+    #Replace #word with word
+    tweet = re.sub(r'#([^\s]+)', r'\1', tweet)
+    #trim
+    tweet = tweet.strip('\'"')
+    # Remove ,'.?!
+    regex = re.compile('[%s]' % re.escape(string.punctuation))
+    tweet = regex.sub('', tweet)
+    # Convert numbers to NUMBERRR
+    tweet = re.sub(" (-?\d+)|(\+1) ", ' NUMBERRR ', tweet)
+    return tweet
+  
+def prepare_Sentiment140(num_class_examples):
+    # Train data
+    positive_start = 800001
+    train_data_negative = pd.read_csv('training.1600000.processed.noemoticon.csv', 
+                                      header=None, delimiter=",", nrows=num_class_examples)
+    train_data_positive = pd.read_csv('training.1600000.processed.noemoticon.csv', 
+                                      header=None, delimiter=",", nrows=num_class_examples, skiprows=positive_start-1)
+    train_data = []
+    for i in range(0, len(train_data_positive[0])):
+      train_data.append([clean_tweet(train_data_negative[5][i]), 0])
+      train_data.append([clean_tweet(train_data_positive[5][i]), 1])
+    shuffle(train_data)
+    
+    # Test data
+    test_data = []
+    test_data_both = pd.read_csv('testdata.manual.2009.06.14.csv', header=None, delimiter=",")
+    for i in range(0, len(test_data_both[0])):
+      if test_data_both[0][i] in (0,4):
+        test_data.append([clean_tweet(test_data_both[5][i]), 0 if test_data_both[0][i]==0 else 1])
+    
+    cPickle.dump([train_data, test_data], open("tweets_clean_{}.pkl".format(num_class_examples), "wb"))
+
+def read_data(num_class_examples):
+    f = file("tweets_clean_{}.pkl".format(num_class_examples), 'rb')
+    train_data, test_data = cPickle.load(f)          # these 3 lines loads the file from disk
+    f.close() 
+    
+    train_sentences = [x[0].split() for x in train_data]
+    train_labels = [x[1] for x in train_data]
+    test_sentences = [x[0].split() for x in test_data]
+    test_labels = [x[1] for x in test_data]
+    
+#     #PUT YOUR READING AND TOKENIZING CODE HERE
+#     train_sentences = [
+#         ['a', 'sentence'],
+#         ['yet', 'another', 'sentence']
+#     ]
+#     train_labels = ['a_sentence', 'another_sentence']
+# 
+#     test_sentences = []
+#     test_labels = []
+
+    return train_sentences, train_labels, test_sentences, test_labels
+  
+def build_model_tf(inputs, word_vecs):
+    recurrent_dim = 512
+    n_classes = 2
+    
+    # Create the embedding layer
+    embeddings = tf.Variable(word_vecs, name='embedding')
+    embed = []
+    for i in range(0, inputs.get_shape()[1].value):
+        embed.append(tf.nn.embedding_lookup(embeddings, inputs[:,i]))
+    
+    # Create the Recurrent layer(s)
+    with tf.variable_scope('rec_cell', initializer=tf.random_normal_initializer(0.0, 0.1)):
+        cell = tf.nn.rnn_cell.GRUCell(num_units=recurrent_dim)
+        outputs, state = tf.nn.rnn(cell, embed, dtype=tf.float32)
+    
+    # Compute the logits
+    W = tf.Variable(tf.zeros([recurrent_dim, n_classes]), name='logits_w')
+    b = tf.Variable(tf.zeros([n_classes]), name='logits_b')
+    logits = tf.matmul(outputs[-1], W) + b
+    
+    return logits
+  
+def one_sentence():
+    # Load the word2index mapping
+    f = file('word2index.pkl', 'rb')
+    word2index, max_words_in_sentence, word_vecs = cPickle.load(f)
+    f.close()
+    
+    # Create the inference model
+    # Create the placeholders
+    inputs = tf.placeholder(tf.int32, (None, max_words_in_sentence), name='inputs')
+
+    # Create the model
+    print 'Creating the computation graph'
+    logits = build_model_tf(inputs, word_vecs)
+    probs = tf.nn.softmax(logits)
+    
+    # Restore model
+    sess = tf.Session()
+    saver = tf.train.Saver(tf.all_variables())
+    saver.restore(sess, os.getcwd() + '/model.sv')
+    
+    # Get output
+    sentence = FLAGS.sentence.split()
+    sentence = encode_sentences([sentence], word2index)
+    sentence = to_np_ndarray(sentence)
+    sentence = np.pad(sentence, [(0,0),(0,max_words_in_sentence - sentence.shape[1])], 'constant')
+    probs_numpy = sess.run(probs, feed_dict={inputs:sentence})
+    print probs_numpy[0][1]
+
+def new_data():
+    # Load the word2index mapping
+    f = file('word2index.pkl', 'rb')
+    word2index, max_words_in_sentence, word_vecs = cPickle.load(f)
+    f.close()
+    
+    # Create the inference model
+    # Create the placeholders
+    inputs = tf.placeholder(tf.int32, (None, max_words_in_sentence), name='inputs')
+
+    # Create the model
+    print 'Creating the computation graph'
+    logits = build_model_tf(inputs, word_vecs)
+    probs = tf.nn.softmax(logits)
+    
+    sess = tf.Session()
+    saver = tf.train.Saver(tf.all_variables())
+    saver.restore(sess, os.getcwd() + '/model.sv')
+    print ''
+    user_input = raw_input("Enter your own text (q to quit): \n")
+    while user_input != 'q':
+        sentence = user_input.split()
+        sentence = encode_sentences([sentence], word2index)
+        sentence = to_np_ndarray(sentence)
+        sentence = np.pad(sentence, [(0,0),(0,max_words_in_sentence - sentence.shape[1])], 'constant')
+        probs_numpy = sess.run(probs, feed_dict={inputs:sentence})
+        print 'Negative: {:.2f}%, Positive: {:.2f}%'.format(probs_numpy[0][0]*100, probs_numpy[0][1]*100)
+        print ''
+        user_input = raw_input("Enter your own text (q to quit): \n")
+
+def save_model(sess, saver, word2index, max_words_in_sentence, word_vecs):
+    saver.save(sess, os.getcwd() + '/model.sv')
+    cPickle.dump([word2index, max_words_in_sentence, word_vecs], open("word2index.pkl", "wb"))
+
+def main():
+    num_class_examples = 500000
+    lr = 0.1
+    n_steps = 100000000
+    mb = 100
+    gc = 1.0
+    print_every = 200
+    save_every = 2000
+    
+    # Get the data, prepare it, and create the word embedding initial matrix
+    train_sentences, train_labels, test_sentences, test_labels = read_data(num_class_examples)
+    word_vecs, word2index = create_word_vecs(train_sentences)
+    train_sentences = encode_sentences(train_sentences, word2index)
+    test_sentences = encode_sentences(test_sentences, word2index)
+    all_sentences = to_np_ndarray(train_sentences + test_sentences)
+    train_sentences = all_sentences[0:len(train_sentences)]
+    test_sentences = all_sentences[-len(test_sentences):]
+#     labels, label2index = encode_labels(train_labels + test_labels)
+#     train_labels = labels[:len(train_labels)]
+#     test_labels = labels[len(train_labels):]
+    max_words_in_sentence = train_sentences.shape[1]
+    
+    
+    # For debug
+    global a
+    a = train_sentences
+
+    # Create the placeholders
+    inputs = tf.placeholder(tf.int32, (None, max_words_in_sentence), name='inputs')
+    labels = tf.placeholder(tf.int32, name='labels')
+
+    # Create the model
+    print 'Creating the computation graph'
+    global_step = tf.Variable(0, trainable=False) 
+    logits = build_model_tf(inputs, word_vecs)
+    
+    # Compute the cost and accuracy
+    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
+      logits, labels, name='cross_entropy_per_example')
+    cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
+    top_k_op = tf.reduce_mean(tf.to_float(tf.nn.in_top_k(logits, labels, 1)))
+    
+    # Create the optimizer
+    print 'Creating the optimization graph nodes'
+    opt = tf.train.GradientDescentOptimizer(lr)
+    grads = opt.compute_gradients(loss=cross_entropy_mean, var_list=tf.trainable_variables())
+    for i in range(0,len(grads)):
+        grads[i] = (tf.clip_by_norm(grads[i][0], gc), grads[i][1])
+    apply_gradient_op = opt.apply_gradients(grads, global_step=global_step)
+    
+    # Init vars, create session, saver
+    saver = tf.train.Saver(tf.trainable_variables())
+    sess = tf.Session()
+    sess.run(tf.initialize_all_variables())
+    
+    # The training loop
+    print 'Training...'
+    curr = 0
+    
+    # Init aggregators
+    cost_sum = 0
+    acc_sum = 0
+    
+    for i in range(1, n_steps):
+        # Get the minibatch
+        batch_inputs = train_sentences[curr:curr+mb]
+        batch_labels = train_labels[curr:curr+mb]
+        
+        # process one minibatch
+        _, c, acc = sess.run([apply_gradient_op, cross_entropy_mean, top_k_op], feed_dict={inputs: batch_inputs, labels: batch_labels})
+        
+        # Add to aggregators
+        cost_sum += c
+        acc_sum += acc
+    
+        # Increase curr
+        curr = (curr + mb) % (2 * num_class_examples)
+        
+        # Do some printing
+        if i % print_every == 0:
+            # Print train values
+            print 'After {} training batches:'.format(i)
+            print 'Train cost: {}'.format(cost_sum / float(print_every))
+            print 'Train accuracy: {}'.format(acc_sum / float(print_every))
+            
+            # Set aggregators to 0
+            cost_sum = 0
+            acc_sum = 0
+            
+            # Get test results
+            test_acc = sess.run(top_k_op, feed_dict={inputs: test_sentences, labels: test_labels})
+            print 'Test accuracy: {}'.format(test_acc)
+            print ''
+        
+        # Save the model
+        if i % save_every == 0:
+            save_model(sess, saver, word2index, max_words_in_sentence, word_vecs)
+
+if __name__ == "__main__":
+    if FLAGS.mode == 'train':
+        #main()
+	print 'To not overwrite the current model, training is not allowed here'
+    elif FLAGS.mode == 'live':
+        new_data()
+    if FLAGS.mode == 'sentence':
+        one_sentence()
+    elif FLAGS.mode == 'prepare':
+        #prepare_Sentiment140(500000)
+	'To not overwrite the current model, this is not allowed here'
@@ -0,0 +1,12 @@
+#!/bin/bash
+#echo "h$1"
+#python rnn_sentiment.py --mode=sentence --sentence="$1"
+str="$1"
+os=$(echo $str| sed 's/_/ /g')
+#echo ${os}
+##strrep=${str//_/ }
+v=$(python rnn_sentiment.py --mode=sentence --sentence="$os" | sed -n '1!p')
+##echo $(python rnn_sentiment.py --mode=sentence --sentence=\"$1\"
+##v=$(python rnn_sentiment.py --mode=sentence --sentence=\"$1\" | sed -n '1!p')
+a=`awk "BEGIN{printf \"%.3f\",$v}"`
+printf '{ "PROCESSOR":"python","ORIGIN":"theano","TYPE":"regression","COMPONENT":"sentiment","VIDX":0,"VALUE":'$a',"PROB":[{"CONFIDENCE":1}]}\n'
@@ -0,0 +1,12 @@
+#!/bin/bash
+#echo "h$1"
+#python rnn_sentiment.py --mode=sentence --sentence="$1"
+str="$1"
+os=$(echo $str| sed 's/_/ /g')
+echo ${os}
+##strrep=${str//_/ }
+v=$(python rnn_sentiment.py --mode=sentence --sentence="$os" | sed -n '1!p')
+##echo $(python rnn_sentiment.py --mode=sentence --sentence=\"$1\"
+##v=$(python rnn_sentiment.py --mode=sentence --sentence=\"$1\" | sed -n '1!p')
+#a=`awk "BEGIN{printf \"%.3f\",$v}"`
+#printf '{ "PROCESSOR":"python","ORIGIN":"theano","TYPE":"regression","COMPONENT":"sentiment","VIDX":0,"VALUE":'$a',"PROB":[{"CONFIDENCE":1}]}\n'
@@ -0,0 +1,2 @@
+REST_FILES=/path/to/download/directory/
+REST_OPENSMILE=/path/to/classifier/directory/