def EmotionAnalyzerSVM(duration, execution_id):
slice_audio_dir = 'audio_tmp'
model_path = 'model.svm'
interval = 10
file_name = str(execution_id)
with open(file_name + '_audio.csv', 'w') as outfile:
columns = [
"from", "to", "next_offset", "Full_Arousal", "Full_Valence",
"Foreground_Arousal", "Foreground_Valence", "Background_Arousal",
"Background_Valence"
]
w = csv.DictWriter(outfile, fieldnames=columns)
w.writeheader()
for i in range(0, int(duration), interval / 2):
from_duration = i
to_duration = interval + i
next_offset = i + interval / 2
chunk = str(from_duration) + "to" + str(to_duration) + "sec"
outfile.write(
str(from_duration) + ',' + str(to_duration) + ',' +
str(next_offset) + ',')
try:
sentiment = aT.fileRegression(
slice_audio_dir + file_name[0:15] + "_" + chunk + "_" +
"S_full" + ".wav", model_path, "svm")[0]
#print("sentiment for Full Spectrum"+chunk+"- Arousal:"+sentiment[0]+"; Valence:"+sentiment[1] )
outfile.write(
str(sentiment[0]) + ',' + str(sentiment[1]) + ',')
except TypeError:
pass
try:
sentiment2 = aT.fileRegression(
slice_audio_dir + file_name[0:15] + "_" + chunk + "_" +
"S_foreground" + ".wav", model_path, "svm")[0]
#print("sentiment for Foreground"+chunk+"- Arousal:"+sentiment2[0]+"; Valence:"+sentiment2[1] )
outfile.write(
str(sentiment2[0]) + ',' + str(sentiment2[1]) + ',')
except TypeError:
pass
try:
sentiment3 = aT.fileRegression(
slice_audio_dir + file_name[0:15] + "_" + chunk + "_" +
"S_background" + ".wav", model_path, "svm")[0]
#print("sentiment for background"+chunk+"- Arousal:"+sentiment3[0]+"; Valence:"+sentiment3[1] )
outfile.write(str(sentiment3[0]) + ',' + str(sentiment3[1]))
except TypeError:
pass
outfile.write("\n")
# EmotionAnalyzerSVM('6495',str(slice_audio_dir),str(model_path),execution_id)
def regressionFolderWrapper(inputFolder, model_type, model_name):
files = "*.wav"
if os.path.isdir(inputFolder):
strFilePattern = os.path.join(inputFolder, files)
else:
strFilePattern = inputFolder + files
wavFilesList = []
wavFilesList.extend(glob.glob(strFilePattern))
wavFilesList = sorted(wavFilesList)
if len(wavFilesList) == 0:
print("No WAV files found!")
return
Results = []
for wavFile in wavFilesList:
R, regressionNames = aT.fileRegression(wavFile, model_name, model_type)
Results.append(R)
Results = numpy.array(Results)
for i, r in enumerate(regressionNames):
[Histogram, bins] = numpy.histogram(Results[:, i])
centers = (bins[0:-1] + bins[1::]) / 2.0
plt.subplot(len(regressionNames), 1, i + 1)
plt.plot(centers, Histogram)
plt.title(r)
plt.show()
def regressionFileWrapper(inputFile, model_type, model_name):
if not os.path.isfile(inputFile):
raise Exception("Input audio file not found!")
R, regressionNames = aT.fileRegression(inputFile, model_name, model_type)
for i in range(len(R)):
print("{0:s}\t{1:.3f}".format(regressionNames[i], R[i]))
def regressionFolderWrapper(inputFolder, model_type, model_name):
files = "*.wav"
if os.path.isdir(inputFolder):
strFilePattern = os.path.join(inputFolder, files)
else:
strFilePattern = inputFolder + files
wavFilesList = []
wavFilesList.extend(glob.glob(strFilePattern))
wavFilesList = sorted(wavFilesList)
if len(wavFilesList) == 0:
print("No WAV files found!")
return
Results = []
for wavFile in wavFilesList:
R, regressionNames = aT.fileRegression(wavFile, model_name, model_type)
Results.append(R)
Results = numpy.array(Results)
for i, r in enumerate(regressionNames):
[Histogram, bins] = numpy.histogram(Results[:, i])
centers = (bins[0:-1] + bins[1::]) / 2.0
plt.subplot(len(regressionNames), 1, i + 1)
plt.plot(centers, Histogram)
plt.title(r)
plt.show()
def regressionFileWrapper(inputFile, model_type, model_name):
if not os.path.isfile(inputFile):
raise Exception("Input audio file not found!")
R, regressionNames = aT.fileRegression(inputFile, model_name, model_type)
for i in range(len(R)):
print("{0:s}\t{1:.3f}".format(regressionNames[i], R[i]))
def regressionFolderWrapperLinearlySeparable(inputFolder, model_type,
model_name):
files = "*.wav"
if os.path.isdir(inputFolder):
strFilePattern = os.path.join(inputFolder, files)
else:
strFilePattern = inputFolder + files
wavFilesList = []
wavFilesList.extend(glob.glob(strFilePattern))
wavFilesList = sorted(wavFilesList)
if len(wavFilesList) == 0:
print("No WAV files found!")
return
Results = []
for wavFile in wavFilesList:
R = aT.fileRegression(wavFile, model_name, model_type)
Results.append(R)
Results = numpy.array(Results)
#Reasonable scatterplot for regression
N = len(Results)
y = numpy.arange(N)
col = numpy.where(Results[:, 0] < .5, 'r', 'b')
plt.scatter(y, Results, c=col, alpha=0.6)
plt.show()
def get_emotions(self, audio_file_path, model_path, model_name):
afp = Path(audio_file_path)
model = Path(model_path) / model_name
if not os.path.exists(Path(model_path)):
print('Model folder does not exist')
return
if not os.path.exists(afp):
print('File does not exist')
return
return aT.fileRegression(str(afp), str(model), 'svm')
def regressionFolderWrapper(inputFolder, model_type, model_name):
files = "*.wav"
if os.path.isdir(inputFolder):
strFilePattern = os.path.join(inputFolder, files)
else:
strFilePattern = inputFolder + files
wavFilesList = []
wavFilesList.extend(glob.glob(strFilePattern))
wavFilesList = sorted(wavFilesList)
if len(wavFilesList) == 0:
print("No WAV files found!")
return
Results = []
SyncFileNames = []
for wavFile in wavFilesList:
R, regressionNames = aT.fileRegression(wavFile, model_name, model_type)
Results.append(R)
SyncFileNames.append(wavFile)
Results = numpy.array(Results)
# for i, r in enumerate(regressionNames):
# [Histogram, bins] = numpy.histogram(Results[:, i])
# centers = (bins[0:-1] + bins[1::]) / 2.0
# plt.subplot(len(regressionNames), 1, i + 1)
# plt.plot(centers, Histogram)
# plt.title(r)
# plt.show()
#Reasonable scatterplot for regression
N = len(Results)
for idx, res in enumerate(Results):
filename = SyncFileNames[idx]
print("Results - {0} : {1}".format(Results[idx], filename))
t = numpy.arange(0.5, N)
y = numpy.arange(N)
col = numpy.where(Results[..., 0] < 0.5, 'r', 'b')
plt.scatter(y, Results, c=col, alpha=0.6)
plt.axhline(y=0.5, color='r', linestyle='--')
plt.show()
'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",
def sentiments(filepath):
results = aT.fileRegression(
filepath,
"/home/mscuser/pyaudio/pyAudioAnalysis/pyAudioAnalysis/data/speechEmotion/",
"svm")
return results
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"))
print("\n\n\n * * * TEST 9 * * * \n\n\n")
aT.featureAndTrainRegression(root_data_path + "pyAudioAnalysis/data/speechEmotion", 1, 1, 0.050, 0.050, "randomforest", "temp.mod", compute_beat=False)
print(aT.fileRegression(root_data_path + "pyAudioAnalysis/data/speechEmotion/01.wav", "temp.mod", "randomforest"))
