def show_open_dialog(self):
self.audioFile = QtGui.QFileDialog.getOpenFileName(
self, 'Open audio file', '', "Audio Files (*.wav)", None,
QtGui.QFileDialog.DontUseNativeDialog)
if self.audioFile != "":
self.featuresTbl.setRowCount(0)
self.featuresTbl.setColumnCount(0)
self.audioClassInput.setText("")
fileName = str(self.audioFile)
self.audio_signal, self.audio_fs = FileReader.read_audio(fileName)
self.silenced_signal, self.audio_fs = self.mfcc.remove_silence(
fileName)
self.fsValLbl.setText(": " + str(self.audio_fs) + " Hz")
self.sampleValLbl.setText(": " + str(len(self.audio_signal)) +
" | " + str(len(self.silenced_signal)) +
" (silenced)")
self.audioFilenameLbl.setText(": " + fileName[fileName.rfind('/') +
1:len(fileName)])
self.audioClassInput.setText(FileReader.get_output_class(fileName))
self.audioPlayBtn.setDisabled(False)
self.extractSaveBtn.setDisabled(False)
self.player.set_audio_source(self.audioFile)
def include_word(self):
if self.inclWordCheck.isChecked():
for i in xrange(self.featuresTbl.rowCount()):
text = str(self.featuresTbl.item(i, 0).text())
self.featuresTbl.setItem(i, 1, QtGui.QTableWidgetItem(str(FileReader.get_output_class(str(text)))))
else:
for i in xrange(self.featuresTbl.rowCount()):
text = str(self.featuresTbl.item(i, 1).text())
self.featuresTbl.setItem(i, 1, QtGui.QTableWidgetItem(str(text[:text.rfind("-")])))
def shuffle_files(self):
self.audio_files = sample(self.audio_files, len(self.audio_files))
for i in xrange(self.featuresTbl.rowCount()):
self.featuresTbl.setItem(
i, 0, QtGui.QTableWidgetItem(str(self.audio_files[i])))
self.featuresTbl.setItem(
i, 1,
QtGui.QTableWidgetItem(
str(FileReader.get_output_class(str(
self.audio_files[i])))))
def run(self):
self.emit(QtCore.SIGNAL("update()"))
self.mfcc.frame_size = int(self.par.frameSizeVal.currentText())
self.mfcc.overlap = self.mfcc.frame_size / 2
for index, file_audio in enumerate(self.audio_files):
file_audio = str(file_audio)
self.audio_signal, self.audio_fs = FileReader.read_audio(
file_audio)
self.silenced_signal, self.audio_fs = self.mfcc.remove_silence(
file_audio)
self.num_frames, self.framed_signal = self.mfcc.frame_blocking(
self.silenced_signal)
self.windowed_signal = self.mfcc.hamm_window(self.framed_signal)
self.fft_signal = self.mfcc.calc_fft(self.windowed_signal)
self.log_energy, self.fbank = self.mfcc.fbank(
self.fft_signal, self.audio_fs)
self.features = self.mfcc.features(self.log_energy)
# var = [st.variance(self.features[:,i]) for i in xrange(self.mfcc.num_filter)]
# [self.all_features.append(self.features[i,:]) for i in xrange(self.features.shape[0])]
# self.variances.append(var)
features = []
if TYPE == 1:
file_id = self.db.insert("files", {"file_path": file_audio})
for i in xrange(self.features.shape[0]):
# [31, 28, 29, 30, 27, 26, 25, 24, 23, 22, 20, 21, 19
# features.append([file_id, i, self.features[i, 1:14], str(self.par.featuresTbl.item(index,1).text())])
features.append([
file_id, i, self.features[
i, [1, 2, 3, 4, 5, 7, 6, 9, 8, 10, 11, 12, 13]],
str(self.par.featuresTbl.item(index, 1).text())
])
self.db.insert_features(features)
else:
output_class_id = self.db.insert(
"output_classes", {
"file_path": file_audio,
"class": str(FileReader.get_output_class(file_audio))
})
for i in xrange(self.features.shape[0]):
features.append(
[output_class_id, i, self.features[i, 1:14]])
self.db.insert_features(features)
self.emit(QtCore.SIGNAL("update()"))
# self.variances = np.asarray(self.variances)
# rata2 = [st.mean(self.variances[:,i]) for i in xrange(self.mfcc.num_filter)]
# self.write_excel(rata2)
# print str(np.sort(rata2))
# print str(np.argsort(rata2))
self.emit(QtCore.SIGNAL("finish()"))
def include_word(self):
if self.inclWordCheck.isChecked():
for i in xrange(self.featuresTbl.rowCount()):
text = str(self.featuresTbl.item(i, 0).text())
self.featuresTbl.setItem(
i, 1,
QtGui.QTableWidgetItem(
str(FileReader.get_output_class(str(text)))))
else:
for i in xrange(self.featuresTbl.rowCount()):
text = str(self.featuresTbl.item(i, 1).text())
self.featuresTbl.setItem(
i, 1, QtGui.QTableWidgetItem(str(text[:text.rfind("-")])))
def show_open_dialog(self):
audioFiles = QtGui.QFileDialog.getOpenFileNames(self, 'Open audio file',
'',
"Audio Files (*.wav)",
None, QtGui.QFileDialog.DontUseNativeDialog)
self.featuresTbl.setColumnWidth(0, 300)
for file in audioFiles:
self.audio_files.append(file)
currentRow = self.featuresTbl.rowCount()
self.featuresTbl.insertRow(currentRow)
self.featuresTbl.setItem(currentRow, 0, QtGui.QTableWidgetItem(str(file)))
self.featuresTbl.setItem(currentRow, 1, QtGui.QTableWidgetItem(str(FileReader.get_output_class(str(file)))))
self.audioFilenameLbl.setText(": " + str(len(self.audio_files)))
def run(self):
self.emit(QtCore.SIGNAL("update()"))
self.mfcc.frame_size = int(self.par.frameSizeVal.currentText())
self.mfcc.overlap = self.mfcc.frame_size / 2
for index, file_audio in enumerate(self.audio_files):
file_audio = str(file_audio)
self.audio_signal, self.audio_fs = FileReader.read_audio(file_audio)
self.silenced_signal, self.audio_fs = self.mfcc.remove_silence(file_audio)
self.num_frames, self.framed_signal = self.mfcc.frame_blocking(self.silenced_signal)
self.windowed_signal = self.mfcc.hamm_window(self.framed_signal)
self.fft_signal = self.mfcc.calc_fft(self.windowed_signal)
self.log_energy, self.fbank = self.mfcc.fbank(self.fft_signal, self.audio_fs)
self.features = self.mfcc.features(self.log_energy)
# var = [st.variance(self.features[:,i]) for i in xrange(self.mfcc.num_filter)]
# [self.all_features.append(self.features[i,:]) for i in xrange(self.features.shape[0])]
# self.variances.append(var)
features = []
if TYPE == 1:
file_id = self.db.insert("files", {"file_path": file_audio})
for i in xrange(self.features.shape[0]):
# [31, 28, 29, 30, 27, 26, 25, 24, 23, 22, 20, 21, 19
# features.append([file_id, i, self.features[i, 1:14], str(self.par.featuresTbl.item(index,1).text())])
features.append([file_id, i, self.features[i, [1, 2, 3, 4, 5, 7, 6, 9, 8, 10, 11, 12, 13]],
str(self.par.featuresTbl.item(index, 1).text())])
self.db.insert_features(features)
else:
output_class_id = self.db.insert("output_classes",
{"file_path": file_audio,
"class": str(FileReader.get_output_class(file_audio))})
for i in xrange(self.features.shape[0]):
features.append([output_class_id, i, self.features[i, 1:14]])
self.db.insert_features(features)
self.emit(QtCore.SIGNAL("update()"))
# self.variances = np.asarray(self.variances)
# rata2 = [st.mean(self.variances[:,i]) for i in xrange(self.mfcc.num_filter)]
# self.write_excel(rata2)
# print str(np.sort(rata2))
# print str(np.argsort(rata2))
self.emit(QtCore.SIGNAL("finish()"))
def show_open_dialog(self):
audioFiles = QtGui.QFileDialog.getOpenFileNames(
self, 'Open audio file', '', "Audio Files (*.wav)", None,
QtGui.QFileDialog.DontUseNativeDialog)
self.featuresTbl.setColumnWidth(0, 300)
for file in audioFiles:
self.audio_files.append(file)
currentRow = self.featuresTbl.rowCount()
self.featuresTbl.insertRow(currentRow)
self.featuresTbl.setItem(currentRow, 0,
QtGui.QTableWidgetItem(str(file)))
self.featuresTbl.setItem(
currentRow, 1,
QtGui.QTableWidgetItem(
str(FileReader.get_output_class(str(file)))))
self.audioFilenameLbl.setText(": " + str(len(self.audio_files)))
def show_open_dialog(self):
audioFiles = QtGui.QFileDialog.getOpenFileNames(self, 'Open audio file',
'',
"Audio Files (*.wav)",
None, QtGui.QFileDialog.DontUseNativeDialog)
for file in audioFiles:
self.indic = 4 if str(file).rfind('4 Detik') != -1 else 8
speaker = str(FileReader.get_output_class(str(file)))
word = speaker[speaker.rfind('-')+1:] if speaker.rfind('-') != -1 else ""
self.audio_files.append(file)
currentRow = self.featuresTbl.rowCount()
self.featuresTbl.insertRow(currentRow)
self.featuresTbl.setItem(currentRow, 0, QtGui.QTableWidgetItem(str(speaker[:speaker.rfind('-')])))
self.featuresTbl.setItem(currentRow, 1, QtGui.QTableWidgetItem(str(word)))
self.audioFilenameLbl.setText(": " + str(len(self.audio_files)))
self.startTestBtn.setDisabled(False)
self.frameSizeVal.setDisabled(False)
def show_open_dialog(self):
audioFiles = QtGui.QFileDialog.getOpenFileNames(
self, 'Open audio file', '', "Audio Files (*.wav)", None,
QtGui.QFileDialog.DontUseNativeDialog)
for file in audioFiles:
self.indic = 4 if str(file).rfind('4 Detik') != -1 else 8
speaker = str(FileReader.get_output_class(str(file)))
word = speaker[speaker.rfind('-') +
1:] if speaker.rfind('-') != -1 else ""
self.audio_files.append(file)
currentRow = self.featuresTbl.rowCount()
self.featuresTbl.insertRow(currentRow)
self.featuresTbl.setItem(
currentRow, 0,
QtGui.QTableWidgetItem(str(speaker[:speaker.rfind('-')])))
self.featuresTbl.setItem(currentRow, 1,
QtGui.QTableWidgetItem(str(word)))
self.audioFilenameLbl.setText(": " + str(len(self.audio_files)))
self.startTestBtn.setDisabled(False)
self.frameSizeVal.setDisabled(False)
def shuffle_files(self):
self.audio_files = sample(self.audio_files, len(self.audio_files))
for i in xrange(self.featuresTbl.rowCount()):
self.featuresTbl.setItem(i, 0, QtGui.QTableWidgetItem(str(self.audio_files[i])))
self.featuresTbl.setItem(i, 1, QtGui.QTableWidgetItem(str(FileReader.get_output_class(str(self.audio_files[i])))))
