def trial_test(path):
'''
create the test ndx file
param:
path : the test file path
'''
data = pd.read_csv(path)
models = []
segments = []
trials = []
enroll_idmap = sidekit.IdMap('task/idmap.h5')
enroll_models = []
for i in range(0, len(enroll_idmap.leftids), 3):
enroll_models.append(enroll_idmap.leftids[i])
print(enroll_models)
for i in range(len(data.index)):
for j in range(5):
ind = data['GroupID'][i] * 5 + j
models.append(enroll_models[ind])
segments.append(data['FileID'][i])
trials.append('nontarget')
key = sidekit.Key(models=np.array(models),
testsegs=np.array(segments),
trials=np.array(trials))
ndx = key.to_ndx()
assert ndx.validate(), 'ndx is not valid'
ndx.write('task/ndx.h5')
def trial_dev(path):
'''
create the dev ndx and key file
param:
path : the annotation file path
'''
data = pd.read_csv(path)
models = []
segments = []
trials = []
enroll_idmap = sidekit.IdMap('task/idmap.h5')
enroll_models = []
for i in range(0, len(enroll_idmap.leftids), 3):
enroll_models.append(enroll_idmap.leftids[i])
print(enroll_models)
for i in range(len(data.index)):
for j in range(5):
ind = data['GroupID'][i] * 5 + j
models.append(enroll_models[ind])
segments.append(data['FileID'][i])
if str(data['SpeakerID'][i]) == enroll_models[ind]:
trials.append('target')
else:
trials.append('nontarget')
key = sidekit.Key(models=np.array(models),
testsegs=np.array(segments),
trials=np.array(trials))
assert key.validate(), 'key is not valid'
key.write('task/dev_key.h5')
ndx = key.to_ndx()
assert ndx.validate(), 'ndx is not valid'
ndx.write('task/dev_ndx.h5')
def compute_eer(args):
print('Compute eer', end='')
key = sidekit.Key(os.getcwd() + '/task/dev_key.h5')
score = sidekit.Scores(os.getcwd() + '/task/dev_score.h5')
print('\rCompute eer done')
dp = sidekit.DetPlot()
prior = sidekit.logit_effective_prior(0.01, 1, 1)
dp.set_system_from_scores(score, key)
minDCF, _, __, ___, eer = sidekit.bosaris.detplot.fast_minDCF(
dp.__tar__[0], dp.__non__[0], prior, normalize=True)
with open('task/dev_result.txt', 'w') as f:
f.write('eer : {:7.2%}\n'.format(eer))
f.write('minDCF : {:7.2%}\n'.format(minDCF))
return eer, minDCF
rsr2015Path = '/info/home/larcher/RSR2015_v1/'
# Default for RSR2015
audioDir = os.path.join(rsr2015Path, 'sph/male')
# Automatically set the number of parallel process to run.
# The number of threads to run is set equal to the number of cores available
# on the machine minus one or to 1 if the machine has a single core.
nbThread = max(multiprocessing.cpu_count() - 1, 1)
# Load IdMap, Ndx, Key from HDF5 files and ubm_list
print('Load task definition')
enroll_idmap = sidekit.IdMap('/info/home/larcher/task/3sesspwd_eval_m_trn.h5')
test_ndx = sidekit.Ndx('/info/home/larcher/task/3sess-pwd_eval_m_ndx.h5')
key = sidekit.Key('/info/home/larcher/task/3sess-pwd_eval_m_key.h5')
with open('/info/home/larcher/task/ubm_list.txt') as inputFile:
ubmList = inputFile.read().split('\n')
# Process the audio to save MFCC on disk
logging.info("Initialize FeaturesExtractor")
extractor = sidekit.FeaturesExtractor(
audio_filename_structure=audioDir + "/{}.wav",
feature_filename_structure="./features/{}.h5",
sampling_frequency=16000,
lower_frequency=133.3333,
higher_frequency=6955.4976,
filter_bank="log",
filter_bank_size=40,
window_size=0.025,
# on the machine minus one or to 1 if the machine has a single core.
nbThread = max(multiprocessing.cpu_count() - 1, 1)
#################################################################
# Load IdMap, Ndx, Key from PICKLE files and ubm_list
#################################################################
print('Load task definition')
enroll_idmap = sidekit.IdMap('task/sre10_coreX-coreX_m_trn.h5', 'hdf5')
nap_idmap = sidekit.IdMap('task/sre04050608_m_training.h5', 'hdf5')
back_idmap = sidekit.IdMap('task/sre10_coreX-coreX_m_back.h5', 'hdf5')
test_ndx = sidekit.Ndx('task/sre10_coreX-coreX_m_ndx.h5', 'hdf5')
test_idmap = sidekit.IdMap('task/sre10_coreX-coreX_m_test.h5', 'hdf5')
keysX = []
for cond in range(9):
keysX.append(
sidekit.Key('task/sre10_coreX-coreX_det{}_key.h5'.format(cond + 1)))
with open('task/ubm_list.txt', 'r') as inputFile:
ubmList = inputFile.read().split('\n')
if train:
# %%
#################################################################
# Process the audio to generate MFCC
#################################################################
print('Create the feature server to extract MFCC features')
fs = sidekit.FeaturesServer(input_dir=audioDir,
input_file_extension='.mfcc',
label_dir='./',
label_file_extension='.lbl',
from_file='spro4',
distribNb = 512 # number of Gaussian distributions for each GMM
JVPD_Path = r'C:\Users\yokoo takaya\Desktop\JVPD'
# Default for RSR2015
audioDir = os.path.join(JVPD_Path, 'JVPD_ALLsound')
# Automatically set the number of parallel process to run.
# The number of threads to run is set equal to the number of cores available
# on the machine minus one or to 1 if the machine has a single core.
nbThread = max(multiprocessing.cpu_count()-1, 1)
print('Load task definition')
enroll_idmap = sidekit.IdMap('idmap_JVPD.h5')
test_ndx = sidekit.Ndx('ndx_JVPD.h5')
key = sidekit.Key('key_JVPD.h5')
with open('JVPD_filename_all.txt') as inputFile:
ubmList = inputFile.read().split('\n')
logging.info("Initialize FeaturesExtractor")
extractor = sidekit.FeaturesExtractor(audio_filename_structure=audioDir+"/{}.wav",
feature_filename_structure="./features_PLP/{}.h5",
sampling_frequency=16000,
lower_frequency=133.3333,
higher_frequency=6955.4976,
filter_bank="lin",
filter_bank_size=40,
window_size=0.025,
shift=0.01,
ceps_number=19,
enroll_idmap.rightids = np.asarray(segments)
enroll_idmap.start = np.empty(enroll_idmap.rightids.shape, dtype='|O')
enroll_idmap.stop = np.empty(enroll_idmap.rightids.shape, dtype='|O')
enroll_idmap.validate()
enroll_idmap.write(
'/home/adit/Desktop/enroll_ids1.h5'
) #DCASE2017-baseline-system-master/HDF5_DCASE/enroll_ids4.h5')
models, segments, targets = [], [], []
with open(
'/home/adit/Desktop/DCASE2017-baseline-system-master/applications/data/TUT-acoustic-scenes-2017-development/evaluation_setup/fold1_evaluate.txt',
'r+') as op:
for i in op:
i = i.replace('audio/', '').replace('.wav', '')
i = i.rstrip('\n').split('\t')
models.append(i[1])
segments.append(i[0])
targets.append('target')
print(len(models))
print(len(segments))
key = sidekit.Key(models=np.array(models),
testsegs=np.array(segments),
trials=np.array(targets))
key.write('/home/adit/Desktop/key1.h5')
ndx = key.to_ndx()
ndx.write('/home/adit/Desktop/ndx1.h5')