def train_gmm(name, vta):
vta = [frame for frame, label in vta if label == name]
gmm = GMM(n_features=36, n_components=1, n_iter=n_iter)
gmm.fit(vta)
while len(gmm.weights) < n_mixies:
mixup(gmm, vta, name)
gmm.save_model('model_voip/vad_%s_sds_mfcc.gmm' % name)
return
def __init__(self, cfg):
self.cfg = cfg
self.audio_recorded_in = []
self.gmm_speech = GMM()
self.gmm_speech.load_model(self.cfg['VAD']['gmm']['speech_model'])
self.gmm_sil = GMM()
self.gmm_sil.load_model(self.cfg['VAD']['gmm']['sil_model'])
self.log_probs_speech = deque(
maxlen=self.cfg['VAD']['gmm']['filter_length'])
self.log_probs_sil = deque(
maxlen=self.cfg['VAD']['gmm']['filter_length'])
self.last_decision = 0.0
if self.cfg['VAD']['gmm']['frontend'] == 'MFCC':
self.front_end = MFCCFrontEnd(
self.cfg['Audio']['sample_rate'],
self.cfg['VAD']['gmm']['framesize'],
self.cfg['VAD']['gmm']['usehamming'],
self.cfg['VAD']['gmm']['preemcoef'],
self.cfg['VAD']['gmm']['numchans'],
self.cfg['VAD']['gmm']['ceplifter'],
self.cfg['VAD']['gmm']['numceps'],
self.cfg['VAD']['gmm']['enormalise'],
self.cfg['VAD']['gmm']['zmeansource'],
self.cfg['VAD']['gmm']['usepower'],
self.cfg['VAD']['gmm']['usec0'],
self.cfg['VAD']['gmm']['usecmn'],
self.cfg['VAD']['gmm']['usedelta'],
self.cfg['VAD']['gmm']['useacc'],
self.cfg['VAD']['gmm']['n_last_frames'],
self.cfg['VAD']['gmm']['lofreq'],
self.cfg['VAD']['gmm']['hifreq'])
else:
raise ASRException('Unsupported frontend: %s' %
(self.cfg['VAD']['gmm']['frontend'], ))
p_sil.join()
print "Sil GMM training finished"
print datetime.datetime.now()
p_speech.join()
print "Speech GMM training finished"
print datetime.datetime.now()
#train_speech_gmm()
#train_sil_gmm()
print '-' * 120
print 'VAD GMM test'
print datetime.datetime.now()
print '-' * 120
gmm_speech = GMM(n_features=0)
gmm_speech.load_model('model_voip/vad_speech_sds_mfcc.gmm')
gmm_sil = GMM(n_features=0)
gmm_sil.load_model('model_voip/vad_sil_sds_mfcc.gmm')
vta = test
print "Length of test data:", len(vta)
print datetime.datetime.now()
accuracy = 0.0
n = 0
for frame, label in vta:
log_prob_speech = gmm_speech.score(frame)
log_prob_sil = gmm_sil.score(frame)