def get_audio_frames(self, file_path):
all_frames = []
for i in xrange(1, self.number_of_samples):
extractor = FeatureExtractor(file_path + "/" + str(i) + ".wav")
all_frames.append(extractor.calculate_mfcc())
return np.vstack(tuple(all_frames))
def get_audio_frames(self, file_path):
all_frames = []
for i in xrange(1, self.number_of_samples):
extractor = FeatureExtractor(file_path + "/" + str(i) + ".wav")
all_frames.append(extractor.calculate_mfcc())
return np.vstack(tuple(all_frames))
def get_emotion(self, file_path):
"""
method to get the emotion of the given audio file
if new_network is set then new network is created
else previous trained network is used to guess the emotion of the audio
"""
self._ann.create_from_file("network_states/fann/fann.net")
extractor = FeatureExtractor(file_path)
mfcc_vectors = extractor.calculate_mfcc()
frame_level_values = []
for each_vector in mfcc_vectors:
output = self._ann.run(each_vector)
if np.array(output) > np.array([0.5]):
frame_level_values.append("happiness")
else:
frame_level_values.append("sadness")
labels_count = Counter(frame_level_values)
label = max(labels_count.iteritems(), key=operator.itemgetter(1))[0]
return label
def _get_mfcc_of_training_set(self):
"""
Reads the mffc feature vectors of the audio
"""
print " -> Calculating mfcc feature vectors..."
mfcc_coeff_vectors_dict = {}
for i in range(1, 151):
extractor = FeatureExtractor(
DATASET_PATH + 'Happiness/HappinessAudios/' + str(i) + '.wav')
mfcc_coeff_vectors = extractor.calculate_mfcc()
mfcc_coeff_vectors_dict.update({str(i): mfcc_coeff_vectors})
for i in range(201, 351):
extractor = FeatureExtractor(
DATASET_PATH + 'Sadness/SadnessAudios/' + str(i - 200) + '.wav')
mfcc_coeff_vectors = extractor.calculate_mfcc()
mfcc_coeff_vectors_dict.update({str(i): mfcc_coeff_vectors})
print " -> mfcc feature vectors found...."
return mfcc_coeff_vectors_dict
def get_emotion(self, file_path):
"""
method to get the emotion of the given audio file
if new_network is set then new network is created
else previous trained network is used to guess the emotion of the audio
"""
self._ann.create_from_file("network_states/fann/fann.net")
extractor = FeatureExtractor(file_path)
mfcc_vectors = extractor.calculate_mfcc()
frame_level_values = []
for each_vector in mfcc_vectors:
output = self._ann.run(each_vector)
if np.array(output) > np.array([0.5]):
frame_level_values.append("happiness")
else:
frame_level_values.append("sadness")
labels_count = Counter(frame_level_values)
label = max(labels_count.iteritems(), key=operator.itemgetter(1))[0]
return label
def test(self):
sadness_correctCount = 0
for i in xrange(150, 200):
extractor = FeatureExtractor(
"../../../Dataset/Sadness/SadnessAudios/" + str(i) + ".wav")
input_frames = extractor.calculate_mfcc()
if self.gmm_object.predict(input_frames) == 1:
sadness_correctCount = sadness_correctCount + 1
print "sadness correct count: ", sadness_correctCount
happiness_correctCount = 0
for i in xrange(150, 200):
extractor = FeatureExtractor(
"../../../Dataset/Happiness/HappinessAudios/" + str(i) + ".wav")
input_frames = extractor.calculate_mfcc()
if self.gmm_object.predict(input_frames) == 0:
happiness_correctCount = happiness_correctCount + 1
print "happiness correct count: ", happiness_correctCount
def main():
print "Calculating mfcc...."
mfcc_coeff_vectors_dict = {}
for i in range(1, 201):
extractor = FeatureExtractor(
'/home/venkatesh/Venki/FINAL_SEM/Project/Datasets/Happiness/HappinessAudios/' + str(i) + '.wav')
mfcc_coeff_vectors = extractor.calculate_mfcc()
mfcc_coeff_vectors_dict.update({str(i): (mfcc_coeff_vectors, mfcc_coeff_vectors.shape[0])})
for i in range(201, 401):
extractor = FeatureExtractor(
'/home/venkatesh/Venki/FINAL_SEM/Project/Datasets/Sadness/SadnessAudios/' + str(i - 200) + '.wav')
mfcc_coeff_vectors = extractor.calculate_mfcc()
mfcc_coeff_vectors_dict.update({str(i): (mfcc_coeff_vectors, mfcc_coeff_vectors.shape[0])})
audio_with_min_frames, min_frames = get_min_frames_audio(
mfcc_coeff_vectors_dict)
processed_mfcc_coeff = preprocess_input_vectors(
mfcc_coeff_vectors_dict, min_frames)
# frames = min_frames
# print frames
# print len(processed_mfcc_coeff['1'])
# for each_vector in processed_mfcc_coeff['1']:
# print len(each_vector)
print "mffcc found..."
classes = ["happiness", "sadness"]
training_data = ClassificationDataSet(
26, target=1, nb_classes=2, class_labels=classes)
# training_data = SupervisedDataSet(13, 1)
try:
network = NetworkReader.readFrom(
'network_state_frame_level_new2_no_pp1.xml')
except:
for i in range(1, 51):
mfcc_coeff_vectors = processed_mfcc_coeff[str(i)]
for each_vector in mfcc_coeff_vectors:
training_data.appendLinked(each_vector, [1])
for i in range(201, 251):
mfcc_coeff_vectors = processed_mfcc_coeff[str(i)]
for each_vector in mfcc_coeff_vectors:
training_data.appendLinked(each_vector, [0])
training_data._convertToOneOfMany()
print "prepared training data.."
print training_data.indim, training_data.outdim
network = buildNetwork(
training_data.indim, 5, training_data.outdim, fast=True)
trainer = BackpropTrainer(network, learningrate=0.01, momentum=0.99)
print "Before training...", trainer.testOnData(training_data)
trainer.trainOnDataset(training_data, 1000)
print "After training...", trainer.testOnData(training_data)
NetworkWriter.writeToFile(
network, "network_state_frame_level_new2_no_pp.xml")
def main():
print "Calculating mfcc...."
mfcc_coeff_vectors_dict = {}
for i in range(1, 201):
extractor = FeatureExtractor('/home/venkatesh/Venki/FINAL_SEM/Project/Datasets/Happiness/HappinessAudios/' + str(i) + '.wav')
mfcc_coeff_vectors = extractor.calculate_mfcc()
mfcc_coeff_vectors_dict.update({str(i): (mfcc_coeff_vectors, mfcc_coeff_vectors.shape[0])})
for i in range(201, 401):
extractor = FeatureExtractor('/home/venkatesh/Venki/FINAL_SEM/Project/Datasets/Sadness/SadnessAudios/' + str(i - 200) + '.wav')
mfcc_coeff_vectors = extractor.calculate_mfcc()
mfcc_coeff_vectors_dict.update({str(i): (mfcc_coeff_vectors, mfcc_coeff_vectors.shape[0])})
audio_with_min_frames, min_frames = get_min_frames_audio(mfcc_coeff_vectors_dict)
processed_mfcc_coeff = preprocess_input_vectors(mfcc_coeff_vectors_dict, min_frames)
frames = min_frames
print "mfcc found...."
classes = ["happiness", "sadness"]
try:
network = NetworkReader.readFrom('network_state_new_.xml')
except:
# Create new network and start Training
training_data = ClassificationDataSet(frames * 26, target=1, nb_classes=2, class_labels=classes)
# training_data = SupervisedDataSet(frames * 39, 1)
for i in range(1, 151):
mfcc_coeff_vectors = processed_mfcc_coeff[str(i)]
training_data.appendLinked(mfcc_coeff_vectors.ravel(), [1])
# training_data.addSample(mfcc_coeff_vectors.ravel(), [1])
for i in range(201, 351):
mfcc_coeff_vectors = processed_mfcc_coeff[str(i)]
training_data.appendLinked(mfcc_coeff_vectors.ravel(), [0])
# training_data.addSample(mfcc_coeff_vectors.ravel(), [0])
training_data._convertToOneOfMany()
network = buildNetwork(training_data.indim, 5, training_data.outdim)
trainer = BackpropTrainer(network, learningrate=0.01, momentum=0.99)
print "Before training...", trainer.testOnData(training_data)
trainer.trainOnDataset(training_data, 1000)
print "After training...", trainer.testOnData(training_data)
NetworkWriter.writeToFile(network, "network_state_new_.xml")
print "*" * 30 , "Happiness Detection", "*" * 30
for i in range(151, 201):
output = network.activate(processed_mfcc_coeff[str(i)].ravel())
# print output,
# if output > 0.7:
# print "happiness"
class_index = max(xrange(len(output)), key=output.__getitem__)
class_name = classes[class_index]
print class_name
def _get_mfcc_of_training_set(self):
"""
Reads the mffc feature vectors of the audio
"""
print " -> Calculating mfcc feature vectors..."
mfcc_coeff_vectors_dict = {}
for i in range(1, 151):
extractor = FeatureExtractor(DATASET_PATH +
'Happiness/HappinessAudios/' +
str(i) + '.wav')
mfcc_coeff_vectors = extractor.calculate_mfcc()
mfcc_coeff_vectors_dict.update({str(i): mfcc_coeff_vectors})
for i in range(201, 351):
extractor = FeatureExtractor(DATASET_PATH +
'Sadness/SadnessAudios/' +
str(i - 200) + '.wav')
mfcc_coeff_vectors = extractor.calculate_mfcc()
mfcc_coeff_vectors_dict.update({str(i): mfcc_coeff_vectors})
print " -> mfcc feature vectors found...."
return mfcc_coeff_vectors_dict
def test(self):
sadness_correctCount = 0
for i in xrange(150, 200):
extractor = FeatureExtractor(
"../../../Dataset/Sadness/SadnessAudios/" + str(i) + ".wav")
input_frames = extractor.calculate_mfcc()
if self.gmm_object.predict(input_frames) == 1:
sadness_correctCount = sadness_correctCount + 1
print "sadness correct count: ", sadness_correctCount
happiness_correctCount = 0
for i in xrange(150, 200):
extractor = FeatureExtractor(
"../../../Dataset/Happiness/HappinessAudios/" + str(i) +
".wav")
input_frames = extractor.calculate_mfcc()
if self.gmm_object.predict(input_frames) == 0:
happiness_correctCount = happiness_correctCount + 1
print "happiness correct count: ", happiness_correctCount
def main():
mfcc_coeff_vectors_dict = {}
for i in range(1, 201):
extractor = FeatureExtractor('../../../Dataset/Happiness/HappinessAudios/' + str(i) + '.wav')
mfcc_coeff_vectors = extractor.calculate_mfcc()
mfcc_coeff_vectors_dict.update({str(i) :(mfcc_coeff_vectors, mfcc_coeff_vectors.shape[0])})
for i in range(201, 401):
extractor = FeatureExtractor('../../../Dataset/Sadness/SadnessAudios/' + str(i - 200) + '.wav')
mfcc_coeff_vectors = extractor.calculate_mfcc()
mfcc_coeff_vectors_dict.update({str(i) :(mfcc_coeff_vectors, mfcc_coeff_vectors.shape[0])})
processed_mfcc_coeff = preprocess_input_vectors(mfcc_coeff_vectors_dict, 0)
# Prepare training dataset
# train_data_file = open("training_data/fann/training_data.data", "w")
# train_data_file.writelines("194226 " + str(36) + " 1\n")
# for i in range(1, 151):
# for each_vector in processed_mfcc_coeff[str(i)]:
# train_data_file.writelines((" ").join(map(str, each_vector)) + "\n")
# train_data_file.writelines("1\n")
#
# for i in range(201, 350):
# for each_vector in processed_mfcc_coeff[str(i)]:
# train_data_file.writelines((" ").join(map(str, each_vector)) + "\n")
# train_data_file.writelines("0\n")
#
# for each_vector in processed_mfcc_coeff[str(350)]:
# train_data_file.writelines((" ").join(map(str, each_vector)) + "\n")
# train_data_file.writelines("0")
#
# train_data_file.close()
#
# print "Data prepared...."
#
# connection_rate = 1
# learning_rate = 0.01
# num_input = 36
# num_hidden = 6
# num_output = 1
#
# desired_error = 0.0001
# max_iterations = 500
# iterations_between_reports = 100
# #
# ann = libfann.neural_net()
# ann.create_sparse_array(connection_rate, (num_input, num_hidden, num_output))
# ann.set_learning_rate(learning_rate)
# ann.set_activation_function_output(libfann.SIGMOID_SYMMETRIC_STEPWISE)
#
# ann.train_on_file("training_data/fann/training_data.data", max_iterations, iterations_between_reports, desired_error)
#
# ann.save("network_states/fann/fann.net")
# print "done!"
# Create neural network from file
ann = libfann.neural_net()
ann.create_from_file("network_states/fann/fann.net") # A trained network ll be loaded
# Test for happiness detection
print "*" * 30, "Happiness Detection", "*" * 30
counter = {
'happiness': 0,
'sadness': 0
}
for i in range(1, 151):
mfcc_coeff_vectors = processed_mfcc_coeff[str(i)]
frame_level_values = []
for each_vector in mfcc_coeff_vectors:
output = ann.run(each_vector)
if np.array(output) > np.array([0.5]):
frame_level_values.append("happiness")
else:
frame_level_values.append("sadness")
labels_count = Counter(frame_level_values)
label = max(labels_count.iteritems(), key=operator.itemgetter(1))[0]
print str(i) + ".wav: " + label
counter[label] = counter[label] + 1
print
print counter
print
#
# # This is test for sadness detection
print "*" * 30, "Sadness Detection", "*" * 30
counter = {
'happiness': 0,
'sadness': 0
}
for i in range(201, 351):
mfcc_coeff_vectors = processed_mfcc_coeff[str(i)]
frame_level_values = []
for each_vector in mfcc_coeff_vectors:
output = ann.run(each_vector)
if np.array(output) > np.array([0.5]):
frame_level_values.append("happiness")
else:
frame_level_values.append("sadness")
labels_count = Counter(frame_level_values)
label = max(labels_count.iteritems(), key=operator.itemgetter(1))[0]
print str(i - 200) + ".wav: " + label
counter[label] = counter[label] + 1
print
print counter