def segmentclassifyFileWrapper(inputWavFile, model_name, model_type):
if not os.path.isfile(model_name):
raise Exception("Input model_name not found!")
if not os.path.isfile(inputWavFile):
raise Exception("Input audio file not found!")
gtFile = ""
if inputWavFile[-4::]==".wav":
gtFile = inputWavFile.replace(".wav", ".segments")
if inputWavFile[-4::]==".mp3":
gtFile = inputWavFile.replace(".mp3", ".segments")
aS.mtFileClassification(inputWavFile, model_name, model_type, True, gtFile)
def func():
res = [flagsInd, classesAll, acc] = aS.mtFileClassification(PATH_TO_WAV, PATH_TO_SVM, "svm", False, PATH_TO_SEGMENTS_FILE)
print res
segments = getSegments(res[0])
print segments
f = open(PATH_TO_DIR + "segments", "w")
f.write(str(segments))
cutSegments(segments)
def run(wavFileName2,bagFile2):
global wavFileName
global bagFile
global xStart
global xEnd
global annotationFlag, annotations, shadesAndSpeaker, greenIndex
global spf, duration, signal
time = 0
segmentDuration = 0
segments = []
# >> Open WAVfile
#----------------------
#wavFileName -> global variable
wavFileName = wavFileName2
bagFile = bagFile2
spf = wave.open(wavFileName,'r')
#Extract Raw Audio from Wav File
signal = spf.readframes(-1)
signal = np.fromstring(signal, 'Int16')
#self.axes.clear()
#Get wavFile duration
frames = spf.getnframes()
rate = spf.getframerate()
duration = frames / float(rate)
# >> Open CSVfile
#----------------------
# check if .csv exists
csvFileName = bagFile.replace(".bag","_audio.csv")
if os.path.isfile(csvFileName):
# print '.csv Found !'
annotationFile = open(csvFileName, 'rb')
read = csv.reader(annotationFile)
for row in read:
row[0] = float(row[0])
row[1] = float(row[1])
annotations.append([row[0], row[1], row[2]])
# get speakers unic colors for annotation plot and ganttChart
for shadeIndex in range(len(annotations)):
if annotations[shadeIndex][2][:8] == 'Speech::':
shadesAndSpeaker.append([annotations[shadeIndex][2], GreenShades[greenIndex]])
if greenIndex > len(GreenShades):
greenIndex = 0
else:
greenIndex = greenIndex + 1
# >> Call Classifier in case CSVFile not exists
#----------------------
else:
# print 'classifier...'
[flagsInd, classesAll, acc] = aS.mtFileClassification(wavFileName, 'svmModelTest', 'svm', False)
# declare classes
[segs, classes] = aS.flags2segs(flagsInd, 1)
lengthClass = len(classesAll)
className = np.arange(lengthClass, dtype=np.float)
for j in range(len(segs)):
# no Annotation for Silence segments
for i in range(len(classesAll)):
if classes[j] == className[i] and classesAll[i] != 'Silence':
annotations.append([segs[j][0]*1000, segs[j][1]*1000, classesAll[i]])
# >> Initialize GUI
#----------------------
qApp = QtWidgets.QApplication(sys.argv)
aw = ApplicationWindow()
aw.setWindowTitle("Audio")
aw.show()
# >> Terminate GUI
#----------------------
sys.exit(qApp.exec_())
def Classify(wavFileName):
#Segmatation and Classification
#os.chdir('Home/Documents/python/audioGraph')
[flagsInd, classesAll, acc] = aS.mtFileClassification(wavFileName, 'svmModelTest', 'svm', False)
print flagsInd, classesAll
def main(argv):
if argv[1] == "-shortTerm":
for i in range(nExp):
[Fs, x] = audioBasicIO.readAudioFile("diarizationExample.wav");
duration = x.shape[0] / float(Fs)
t1 = time.clock()
F = audioFeatureExtraction.stFeatureExtraction(x, Fs, 0.050*Fs, 0.050*Fs);
t2 = time.clock()
perTime1 = duration / (t2-t1); print "short-term feature extraction: {0:.1f} x realtime".format(perTime1)
elif argv[1] == "-classifyFile":
for i in range(nExp):
[Fs, x] = audioBasicIO.readAudioFile("diarizationExample.wav");
duration = x.shape[0] / float(Fs)
t1 = time.clock()
aT.fileClassification("diarizationExample.wav", "svmSM","svm")
t2 = time.clock()
perTime1 = duration / (t2-t1); print "Mid-term feature extraction + classification \t {0:.1f} x realtime".format(perTime1)
elif argv[1] == "-mtClassify":
for i in range(nExp):
[Fs, x] = audioBasicIO.readAudioFile("diarizationExample.wav");
duration = x.shape[0] / float(Fs)
t1 = time.clock()
[flagsInd, classesAll, acc] = aS.mtFileClassification("diarizationExample.wav", "svmSM", "svm", False, '')
t2 = time.clock()
perTime1 = duration / (t2-t1); print "Fix-sized classification - segmentation \t {0:.1f} x realtime".format(perTime1)
elif argv[1] == "-hmmSegmentation":
for i in range(nExp):
[Fs, x] = audioBasicIO.readAudioFile("diarizationExample.wav");
duration = x.shape[0] / float(Fs)
t1 = time.clock()
aS.hmmSegmentation('diarizationExample.wav', 'hmmRadioSM', False, '')
t2 = time.clock()
perTime1 = duration / (t2-t1); print "HMM-based classification - segmentation \t {0:.1f} x realtime".format(perTime1)
elif argv[1] == "-silenceRemoval":
for i in range(nExp):
[Fs, x] = audioBasicIO.readAudioFile("diarizationExample.wav");
duration = x.shape[0] / float(Fs)
t1 = time.clock()
[Fs, x] = audioBasicIO.readAudioFile("diarizationExample.wav");
segments = aS.silenceRemoval(x, Fs, 0.050, 0.050, smoothWindow = 1.0, Weight = 0.3, plot = False)
t2 = time.clock()
perTime1 = duration / (t2-t1); print "Silence removal \t {0:.1f} x realtime".format(perTime1)
elif argv[1] == "-thumbnailing":
for i in range(nExp):
[Fs1, x1] = audioBasicIO.readAudioFile("scottish.wav")
duration1 = x1.shape[0] / float(Fs1)
t1 = time.clock()
[A1, A2, B1, B2, Smatrix] = aS.musicThumbnailing(x1, Fs1, 1.0, 1.0, 15.0) # find thumbnail endpoints
t2 = time.clock()
perTime1 = duration1 / (t2-t1); print "Thumbnail \t {0:.1f} x realtime".format(perTime1)
elif argv[1] == "-diarization-noLDA":
for i in range(nExp):
[Fs1, x1] = audioBasicIO.readAudioFile("diarizationExample.wav")
duration1 = x1.shape[0] / float(Fs1)
t1 = time.clock()
aS.speakerDiarization("diarizationExample.wav", 4, LDAdim = 0, PLOT = False)
t2 = time.clock()
perTime1 = duration1 / (t2-t1); print "Diarization \t {0:.1f} x realtime".format(perTime1)
elif argv[1] == "-diarization-LDA":
for i in range(nExp):
[Fs1, x1] = audioBasicIO.readAudioFile("diarizationExample.wav")
duration1 = x1.shape[0] / float(Fs1)
t1 = time.clock()
aS.speakerDiarization("diarizationExample.wav", 4, PLOT = False)
t2 = time.clock()
perTime1 = duration1 / (t2-t1); print "Diarization \t {0:.1f} x realtime".format(perTime1)
def run(wavFileName2,bagFile2):
time = 0
segmentDuration = 0
segments = []
# >> Open WAVfile
#----------------------
#audioGlobals.wavFileName -> global variable
audioGlobals.wavFileName = wavFileName2
audioGlobals.bagFile = bagFile2
audioGlobals.spf = wave.open(audioGlobals.wavFileName,'r')
#Extract Raw Audio from Wav File
audioGlobals.signal = audioGlobals.spf.readframes(-1)
audioGlobals.signal = np.fromstring(audioGlobals.signal, 'Int16')
#self.axes.clear()
#Get wavFile audioGlabals.duration
frames = audioGlobals.spf.getnframes()
rate = audioGlobals.spf.getframerate()
audioGlobals.duration = frames / float(rate)
# >> Open CSVfile
#----------------------
# check if .csv exists
csvFileName = audioGlobals.bagFile.replace(".bag","_audio.csv")
if os.path.isfile(csvFileName):
annotationFile = open(csvFileName, 'rb')
read = csv.reader(annotationFile)
for row in read:
row[0] = float(row[0])
row[1] = float(row[1])
audioGlobals.annotations.append([row[0], row[1], row[2]])
# get speakers unic colors for annotation plot and ganttChart
#print len(audioGlobals.GreenShades)
for shadeIndex in range(len(audioGlobals.annotations)):
if audioGlobals.annotations[shadeIndex][2][:8] == 'Speech::':
#print audioGlobals.greenIndex, len(audioGlobals.GreenShades)-1
if audioGlobals.greenIndex >= (len(audioGlobals.GreenShades)-1):
audioGlobals.greenIndex = 0
else:
audioGlobals.greenIndex = audioGlobals.greenIndex + 1
#print audioGlobals.greenIndex, shadeIndex
audioGlobals.shadesAndSpeaker.append([audioGlobals.annotations[shadeIndex][2], audioGlobals.GreenShades[audioGlobals.greenIndex]])
# >> Call Classifier in case CSVFile not exists
#----------------------
else:
[flagsInd, classesAll, acc,CM] = aS.mtFileClassification(audioGlobals.wavFileName, os.path.abspath('audio/ClassifierMethods/svmModelTest'), 'svm', False)
# declare classes
[segs, classes] = aS.flags2segs(flagsInd, 1)
lengthClass = len(classesAll)
className = np.arange(lengthClass, dtype=np.float)
for j in range(len(segs)):
# no Annotation for Silence segments
for i in range(len(classesAll)):
if classes[j] == className[i] and classesAll[i] != 'Silence':
audioGlobals.annotations.append([segs[j][0]*1000, segs[j][1]*1000, classesAll[i]])
# >> Write annotations in csv file
csvFileName = audioGlobals.bagFile.replace(".bag","_audio.csv")
annotationFile = open(csvFileName, 'w')
write = csv.writer(annotationFile)
write.writerows(audioGlobals.annotations)
annotationFile.close()
def save_out(test_file):
[flags_ind, classes_all, acc] = aS.mtFileClassification(test_file, args.model, "knn", False)
np.save(test_file, flags_ind)
return classes_all
print("\n\n\n * * * TEST 2 * * * \n\n\n")
[Fs, x] = audioBasicIO.readAudioFile(root_data_path + "pyAudioAnalysis/data/doremi.wav")
x = audioBasicIO.stereo2mono(x)
specgram, TimeAxis, FreqAxis = audioFeatureExtraction.stSpectogram(x, Fs, round(Fs * 0.040), round(Fs * 0.040), True)
print("\n\n\n * * * TEST 3 * * * \n\n\n")
[Fs, x] = audioBasicIO.readAudioFile(root_data_path + "pyAudioAnalysis/data/doremi.wav")
x = audioBasicIO.stereo2mono(x)
specgram, TimeAxis, FreqAxis = audioFeatureExtraction.stChromagram(x, Fs, round(Fs * 0.040), round(Fs * 0.040), True)
print("\n\n\n * * * TEST 4 * * * \n\n\n")
aT.featureAndTrain([root_data_path +"SM/speech",root_data_path + "SM/music"], 1.0, 1.0, 0.2, 0.2, "svm", "temp", True)
print("\n\n\n * * * TEST 5 * * * \n\n\n")
[flagsInd, classesAll, acc, CM] = aS.mtFileClassification(root_data_path + "pyAudioAnalysis/data//scottish.wav", root_data_path + "pyAudioAnalysis/data/svmSM", "svm", True, root_data_path + 'pyAudioAnalysis/data/scottish.segments')
print("\n\n\n * * * TEST 6 * * * \n\n\n")
aS.trainHMM_fromFile(root_data_path + 'radioFinal/train/bbc4A.wav', root_data_path + 'radioFinal/train/bbc4A.segments', 'hmmTemp1', 1.0, 1.0)
aS.trainHMM_fromDir(root_data_path + 'radioFinal/small', 'hmmTemp2', 1.0, 1.0)
aS.hmmSegmentation(root_data_path + 'pyAudioAnalysis/data//scottish.wav', 'hmmTemp1', True, root_data_path + 'pyAudioAnalysis/data//scottish.segments') # test 1
aS.hmmSegmentation(root_data_path + 'pyAudioAnalysis/data//scottish.wav', 'hmmTemp2', True, root_data_path + 'pyAudioAnalysis/data//scottish.segments') # test 2
print("\n\n\n * * * TEST 7 * * * \n\n\n")
aT.featureAndTrainRegression(root_data_path + "pyAudioAnalysis/data/speechEmotion", 1, 1, 0.050, 0.050, "svm_rbf", "temp.mod", compute_beat=False)
print(aT.fileRegression(root_data_path + "pyAudioAnalysis/data/speechEmotion/01.wav", "temp.mod", "svm_rbf"))
print("\n\n\n * * * TEST 8 * * * \n\n\n")
aT.featureAndTrainRegression(root_data_path + "pyAudioAnalysis/data/speechEmotion", 1, 1, 0.050, 0.050, "svm", "temp.mod", compute_beat=False)
print(aT.fileRegression(root_data_path + "pyAudioAnalysis/data/speechEmotion/01.wav", "temp.mod", "svm"))
