def plot_wavefile(fname, target_rate=None):
""" 绘制wav文件
Args:
fname (str): 文件名
target_rate (int.): 信号的绘图采样率, 可选
"""
rate, signal = read_signal(fname)
if not target_rate:
target_rate = rate
signal = util.set_frame_rate(signal, rate, target_rate)
#signal = util.slice(signal, 1000, 60*10, 60*15)
plot_signal(signal, target_rate)
# convert
ary_sound = sp.fromstring(data_sound, sp.int16)
ary_noise = sp.fromstring(data_noise, sp.int16)
int32_ary_sound = sp.int32(ary_sound)
int32_ary_noise = sp.int32(ary_noise)
ary2 = sp.int16(int32_ary_sound + int32_ary_noise)
data2 = ary2.tostring()
synth.writeframes(data2)
remain = remain - s
sound.close()
noise.close()
synth.close()
infile = 'tools/sound/noisy.wav'
signal, params = read_signal(infile, WINSIZE)
nf = len(signal) / (WINSIZE / 2) - 1
sig_out = sp.zeros(len(signal), sp.float32)
window = sp.hanning(WINSIZE)
ms = MinimumStatistics(WINSIZE, window, params[2])
NP_lambda = compute_avgpowerspectrum(signal[0:WINSIZE * int(params[2] / float(WINSIZE) / 3.0)],
WINSIZE, window)
ms.init_noise_profile(NP_lambda)
ss = JointMap(WINSIZE, window)
for no in xrange(nf):
frame = get_frame(signal, WINSIZE, no)
n_pow = ms.compute(frame, no)
res = ss.compute_by_noise_pow(frame, n_pow)
add_signal(sig_out, res, WINSIZE, no)
window = winfunc(size)
s = s[0:size]
shat = shat[0:size]
s_amp = np.absolute(np.fft.fftpack.fft(s * window))
shat_amp = np.absolute(np.fft.fftpack.fft(shat * window))
return np.sqrt(np.mean((np.log10(s_amp / shat_amp) * 10.0) ** 2.0))
def segmental_log_spectrum_distance(s, shat, winsize, winfunc):
size = min(len(s), len(shat))
nf = size / (winsize / 2) - 1
ret = []
for no in xrange(nf):
s_i = get_frame(s, winsize, no)
shat_i = get_frame(shat, winsize, no)
ret.append(log_spectrum_distance(s_i, shat_i, winfunc))
return ret
if __name__ == "__main__":
import sys
winsize = int(sys.argv[1])
s = read_signal(sys.argv[2], winsize)[0]
shat = read_signal(sys.argv[3], winsize)[0]
sissd = segmental_itakura_saito_spectrum_distance(s, shat, winsize, np.hanning)
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(sissd)
plt.show()
#convert
ary_sound = sp.fromstring(data_sound, sp.int16)
ary_noise = sp.fromstring(data_noise, sp.int16)
int32_ary_sound = sp.int32(ary_sound)
int32_ary_noise = sp.int32(ary_noise)
ary2 = sp.int16(int32_ary_sound + int32_ary_noise)
data2 = ary2.tostring()
synth.writeframes(data2)
remain = remain - s
sound.close()
noise.close()
synth.close()
infile = 'tools/sound/noisy.wav'
signal, params = read_signal(infile, WINSIZE)
nf = len(signal) / (WINSIZE / 2) - 1
sig_out = sp.zeros(len(signal), sp.float32)
window = sp.hanning(WINSIZE)
ms = MinimumStatistics(WINSIZE, window, params[2])
NP_lambda = compute_avgpowerspectrum(
signal[0:WINSIZE * int(params[2] / float(WINSIZE) / 3.0)], WINSIZE,
window)
ms.init_noise_profile(NP_lambda)
ss = JointMap(WINSIZE, window)
for no in xrange(nf):
frame = get_frame(signal, WINSIZE, no)
n_pow = ms.compute(frame, no)
res = ss.compute_by_noise_pow(frame, n_pow)
add_signal(sig_out, res, WINSIZE, no)
s = s[0:size]
shat = shat[0:size]
s_amp = np.absolute(np.fft.fftpack.fft(s * window))
shat_amp = np.absolute(np.fft.fftpack.fft(shat * window))
return np.sqrt(np.mean((np.log10(s_amp / shat_amp) * 10.0)**2.0))
def segmental_log_spectrum_distance(s, shat, winsize, winfunc):
size = min(len(s), len(shat))
nf = size / (winsize / 2) - 1
ret = []
for no in xrange(nf):
s_i = get_frame(s, winsize, no)
shat_i = get_frame(shat, winsize, no)
ret.append(log_spectrum_distance(s_i, shat_i, winfunc))
return ret
if __name__ == "__main__":
import sys
winsize = int(sys.argv[1])
s = read_signal(sys.argv[2], winsize)[0]
shat = read_signal(sys.argv[3], winsize)[0]
sissd = segmental_itakura_saito_spectrum_distance(s, shat, winsize,
np.hanning)
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(sissd)
plt.show()
