def fit_adap(data, ubm, save_path):
print('Generating GMMs...')
msa = em.GMMMachine(64, 60)
egy = em.GMMMachine(64, 60)
msa_trainer = em.MAP_GMMTrainer(ubm, relevance_factor=10)
egy_trainer = em.MAP_GMMTrainer(ubm, relevance_factor=10)
em.train(msa_trainer,
msa,
data['f'],
max_iterations=14,
convergence_threshold=0.001)
em.train(egy_trainer,
egy,
data['m'],
max_iterations=14,
convergence_threshold=0.001)
msa.save(HDF5File(save_path + 'msa.h5', 'w'))
egy.save(HDF5File(save_path + 'egy.h5', 'w'))
def predict_ubm(data, model_path):
try:
msa = em.GMMMachine(HDF5File(model_path + 'msa.h5'))
egy = em.GMMMachine(HDF5File(model_path + 'egy.h5'))
# ubm = joblib.load(model_path + 'ubm.joblib')
# msa = joblib.load(model_path + 'msa.joblib')
# egy = joblib.load(model_path + 'egy.joblib')
except:
print("Model not found.")
exit()
return {
'm':
map(lambda x: (msa.log_likelihood(x), egy.log_likelihood(x)),
data['m']),
'f':
map(lambda x: (msa.log_likelihood(x), egy.log_likelihood(x)),
data['f'])
}
def fit_ubm(switch_data, non_switch_data, num_components, save_path):
print('Generating UBM...')
all_data = np.concatenate((switch_data, non_switch_data))
ubm = em.GMMMachine(num_components, all_data.shape[1])
ubm_trainer = em.ML_GMMTrainer(True, True, True)
em.train(ubm_trainer,
ubm,
all_data,
max_iterations=12,
convergence_threshold=0.001)
ubm.save(HDF5File(save_path + 'ubm.h5', 'w'))
return ubm
def fit_ubm(data, save_path):
print('Generating UBM...')
all_data = np.concatenate((data['m'], data['f']))
ubm = em.GMMMachine(64, 60)
ubm_trainer = em.ML_GMMTrainer(True, True, True)
em.train(ubm_trainer,
ubm,
all_data,
max_iterations=12,
convergence_threshold=0.001)
ubm.save(HDF5File(save_path + 'ubm.h5', 'w'))
# ubm = GaussianMixture(128, covariance_type='diag', init_params='random', warm_start=True, max_iter=12, verbose=1).fit(all_data)
# joblib.dump(ubm, save_path + 'ubm.joblib')
return ubm
def fit_adap(switch_data, non_switch_data, ubm, num_components, save_path):
print('Generating GMMs...')
switch_gmm = em.GMMMachine(num_components, switch_data.shape[1])
# non_switch_gmm = em.GMMMachine(num_components, switch_data.shape[1])
switch_trainer = em.MAP_GMMTrainer(ubm,
relevance_factor=10,
update_variances=False,
update_weights=False)
# non_switch_trainer = em.MAP_GMMTrainer(ubm, relevance_factor=10, update_variances=False, update_weights=False)
em.train(switch_trainer,
switch_gmm,
switch_data,
max_iterations=14,
convergence_threshold=0.001)
# em.train(non_switch_trainer, non_switch_gmm, non_switch_data, max_iterations=14,
# convergence_threshold=0.001)
switch_gmm.save(HDF5File(save_path + 'switch.h5', 'w'))
# non_switch_gmm.save(HDF5File(save_path + 'non_switch.h5', 'w'))
return switch_gmm
help='Path to load model from, must end in .joblib')
args = parser.parse_args()
if __name__ == '__main__':
if args.extract:
data.extract_with_test_utterance(args.window * 16, args.num_features)
if args.train:
switch_data, non_switch_data = data.load(args.window,
args.num_features)
ubm = classify.fit_ubm(switch_data, non_switch_data,
args.num_components, args.save_path)
switch_gmm = classify.fit_adap(switch_data, non_switch_data, ubm,
args.num_components, args.save_path)
if args.test:
test_data = data.load_qual_test()
# switch_data, non_switch_data = data.load(args.window, args.num_features, test=True)
if not args.train:
try:
switch_gmm = em.GMMMachine(
HDF5File(args.load_path + 'switch.h5'))
# non_switch_gmm = em.GMMMachine(HDF5File(args.load_path + 'non_switch.h5'))
except:
print("Models not found.")
exit()
ll = classify.switch_ll(test_data, switch_gmm)
evaluate.qual_test(ll, 1)
# scores = classify.predict(switch_data, non_switch_data, switch_gmm, non_switch_gmm)
# Y,Y_pred = evaluate.get_predictions(scores)
# evaluate.evaluate(Y, Y_pred)
# evaluate.confusion_matrix(Y, Y_pred)