def create_data(sig, label_1, label_2):
mfcc = get_mfcc(sig,
freq,
winstep=window_step,
winlen=window_size,
nfft=2048,
lowfreq=lowfreq,
highfreq=highfreq,
numcep=size,
nfilt=size + 2)
# One-hot encoding
labels = np.zeros((len(mfcc), N_classes_1 + N_classes_2))
labels[:, label_dic[label_1]] = 1
labels[:, label_dic[label_2]] = 1
return mfcc, labels
def create_data(sig, label):
mfcc = get_mfcc(sig,
freq,
winstep=window_step,
winlen=window_size,
nfft=2048,
lowfreq=lowfreq,
highfreq=highfreq,
numcep=size,
nfilt=size + 2)
# One-hot encoding
num_label = np.zeros((len(mfcc), N_classes))
num_label[:, label_dic[label]] = 1
# Direct encoding
# num_label = label_dic[label] * np.ones(len(mfcc))
return mfcc, num_label
def create_data(sig, label):
mfcc = get_mfcc(sig,
freq,
winstep=window_step,
winlen=window_size,
nfft=2048,
lowfreq=lowfreq,
highfreq=highfreq,
numcep=size,
nfilt=size + 2)
# One-hot encoding
num_label = np.zeros((len(mfcc), N_classes))
num_label[:, label_dic[label]] = 1
# Direct encoding
# num_label = label_dic[label] * np.ones(len(mfcc))
time_per_occurrence_class[label_dic[label]].append(
(stop - start) / (10.0**7))
return mfcc, num_label
def create_data(sig, label):
mfcc = get_mfcc(
sig,
freq,
winstep=window_step,
winlen=window_size,
nfft=2048,
lowfreq=lowfreq,
highfreq=highfreq,
numcep=size,
nfilt=size + 2,
)
# One-hot encoding
num_label = np.zeros((len(mfcc), N_classes))
num_label[:, label_dic[label]] = 1
# Direct encoding
# num_label = label_dic[label] * np.ones(len(mfcc))
return mfcc, num_label
def create_data(sig, network_type):
if network_type == "DNN":
mfcc = get_mfcc(signal,
freq,
winstep=window_step,
winlen=window_size,
nfft=2048,
lowfreq=lowfreq,
highfreq=highfreq,
numcep=size,
nfilt=size + 2)
elif network_type == "CNN":
mfcc, energy = MFSC(signal,
freq,
winstep=window_step,
nfft=2048,
lowfreq=100,
highfreq=highfreq,
nfilt=size)
return mfcc
def create_data(sig, label):
mfcc = get_mfcc(sig, freq, winstep=window_step, winlen=window_size, nfft=2048, lowfreq=lowfreq,
highfreq=highfreq, numcep=size, nfilt=size+2)
num_label = label_dic[label]*np.ones(len(mfcc))
time_per_occurrence_class[label_dic[label]].append((stop - start) / (10.0 ** 7))
return mfcc, num_label
for j in xrange(len(lines)):
try:
cur_line = lines[j].split()
start = float(cur_line[0])
stop = float(cur_line[1])
label = cur_line[2]
if "WS" in lab_name:
length = stop - start
else:
length = (stop - start) / 10.0 ** 7
audio = f.read_frames(freq * length)
if label in label_dic:
if time < threshold:
# energy = np.sum(audio ** 2, 0) / len(audio)
signal = audio # audio/math.sqrt(energy)
mfcc = get_mfcc(signal, freq, winstep=window_step, winlen=window_size, nfft=2048, lowfreq=lowfreq,
highfreq=highfreq, numcep=size, nfilt=size + 2)
if compute_delta == "True":
d1_mfcc = np.zeros((mfcc.shape[0]-1,mfcc.shape[1]))
for k in range(mfcc.shape[0]-1):
d1_mfcc[k,:] = mfcc[k+1,:] - mfcc[k,:]
mfcc = mfcc[1:,:]
N_iter = np.floor((len(mfcc) - N) / slide)
# apply context window
if (length/window_step) > N:
time_per_occurrence_class[label_dic[label]].append(length)
time = np.sum(time_per_occurrence_class[label_dic[label]])
mfcc_matrix = np.zeros((1, size * N))
for k in range(int(N_iter)):
mfcc_vec = []
for kk in range(N):
mfcc_vec = np.concatenate((mfcc_vec, mfcc[k * slide + kk, :]))
if "WS" in lab_name:
length = stop - start
else:
length = (stop - start) / 10.0**7
audio = f.read_frames(freq * length)
if label in label_dic:
time_per_occurrence_class[label_dic[label]].append(length)
time = np.sum(time_per_occurrence_class[label_dic[label]])
if time < threshold:
# energy = np.sum(audio ** 2, 0) / len(audio)
signal = audio # audio/math.sqrt(energy)
mfcc = get_mfcc(signal,
freq,
winstep=window_step,
winlen=window_size,
nfft=2048,
lowfreq=lowfreq,
highfreq=highfreq,
numcep=size,
nfilt=size + 2)
if compute_delta == "True":
d1_mfcc = np.zeros(
(mfcc.shape[0] - 1, mfcc.shape[1]))
for k in range(mfcc.shape[0] - 1):
d1_mfcc[k, :] = mfcc[k + 1, :] - mfcc[k, :]
mfcc = mfcc[1:, :]
N_iter = np.floor((len(mfcc) - N) / slide)
# apply context window
if (length / window_step) > N:
mfcc_matrix = np.zeros((1, size * N))
d1_matrix = np.zeros((1, size * N))
