def save_enrolled_speakers(path, clients):
# Save enrolled PLDA models to path.
Helper.create_folder(path)
for i, client in enumerate(clients):
client.dump(path+'client-'+str(i)+'.npy')
print('clients saved!')
return
def save_enrolled_speakers(path, clients):
# Save enrolled PLDA models to path.
Helper.create_folder(path)
for i, client in enumerate(clients):
with bob.io.base.HDF5File(path + 'client-' + str(i) + '.hdf5',
'w') as f:
client.save(f)
print('clients saved!')
return
def main():
# step 0. initial
args = get_args()
output_folder_path = Helper.create_folder(args.output_folder_path)
logging.basicConfig(
level = logging.DEBUG, \
filename = output_folder_path + 'log.txt', \
format = '%(asctime)s - %(name)s[%(filename)s:%(lineno)d] - %(levelname)s - %(message)s' \
)
'''
# step 1. construct training and test file-lists
print('step1...')
train_filename, test_filename = ['core.trn'], ['8conv.trn']
train_files, test_files = construct_data(args.data_path, args.trn_path, train_filename, test_filename)
# step 2. extract mfcc
print('step2...')
train_features = extract_features(train_files, len(train_files['filename']), args.frame_size, args.overlap_size)
test_features = extract_features(test_files, len(test_files['filename']), args.frame_size, args.overlap_size)
Helper.save(train_features, 'train_core_all.pkl')
Helper.save(test_features, 'test_features_all.pkl')
'''
train_features = Helper.load('train_core_all.pkl')
test_features = Helper.load('test_features_all.pkl')
# step 3. preprocess
print('step3...')
train_features, test_features = preproces_features(train_features, test_features) # normalize
train_features = extra_prepro(train_features, args.train_sep_num) # separate training data
# #of speakers x 4 x 256 x 39
# step 4. training
print('step4...')
iv = IVector( \
number_of_gaussians = 128, \
gmm_training_iterations = 20, \
use_whitening = True, \
use_wccn = False, \
use_lda = True, \
lda_dim = 100, \
use_pinv = True, \
subspace_dimension_of_t = 300,
tv_training_iterations = 5, \
use_plda = True, \
plda_dim_F = 50, \
plda_dim_G = 50, \
plda_training_iterations= 50, \
)
#iv.train_projector(train_features, output_folder_path + 'iv-all-plda-' + str(args.train_sep_num) + '.hdf5')
iv.load_projector(output_folder_path + 'iv-all-plda.hdf5')
# step 4.5 train autoencoder
#train_iv = get_train_iv(train_features, iv, 'train_iv_all.npy') # shape: (#of speakers x 4) x 100
train_iv = numpy.load('train_iv_all.npy')
train_autoencoder(train_iv)
# step 5. enroll
print('step5...')
#clients = read_enrolled_speakers('clients-auto/', iv, len(test_features))
model_dir = tf.train.latest_checkpoint('ckpt/')
clients = enroll_features(iv, model_dir, test_features, args.number_of_test_cases)
#save_enrolled_speakers('clients-auto/', clients)
# step 6. test
print('step6...')
scores, labels = test_features_(iv, model_dir, clients, test_features, args.number_of_test_cases)
# step 7. summary
print('step7...')
p_scores, n_scores = scores[numpy.where(labels == True)].astype(numpy.double), scores[numpy.where(labels == False)[0]].astype(numpy.double)
threshold = bob.measure.eer_threshold(n_scores, p_scores)
far, frr = bob.measure.farfrr(n_scores, p_scores, threshold)
Helper.output(output_folder_path + 'result.txt', 'threshold = %f, eer = %f%%, far = %f%%, frr = %f%%\n' % ( \
threshold, max(far, frr) * 100, far * 100, frr * 100))
Helper.generate_det_curve(p_scores, n_scores, output_folder_path + 'det_curve.png')
