语音可视化
今天我想复现一下，文中语谱图提取部分的代码
由于输入的语音有单通道和双通道之分，处理方式是单通道不变，双通道只取一个通道的信息。附上代码：
import wave as we
import numpy as np
import matplotlib.pyplot as plt
def wavread(path):
wavfile = we.open(path,"rb")
params = wavfile.getparams()
nchannels,samplewidth,framerate,nframes=params[:4]
datawav = wavfile.readframes(nframes)
wavfile.close()
wave_data = np.fromstring(datawav,dtype = np.short)
if nchannels==1: wave_data.shape=-1,1
if nchannels==2: wave_data.shape=-1,2
wave_data = wave_data.T
time = np.arange(0, nframes) * (1.0/framerate)
return wave_data[0],time
path = "1.wav"
wavdata,wavtime = wavread(path)
plt.plot(wavtime, wavdata,color = 'blue')
plt.show()
得到如下的时域波形图
然后对原始语音信号处理，得到4k范围内的频率信号。为了理解操作过程，对fft变换的结果进行了总结：
def fft_4K(path):
# gain wav data
wavfile = we.open(path,"rb")
params = wavfile.getparams()
nchannels,samplewidth,framerate,nframes=params[:4]
datawav = wavfile.readframes(nframes)
wavfile.close()
wave_data = np.fromstring(datawav,dtype = np.short)
if nchannels==1: wave_data.shape=-1,1
if nchannels==2: wave_data.shape=-1,2
wave_data = wave_data.T
# gain fft
df=framerate/(float)(nframes-1)
freq=[df*n for n in range(0,nframes)]
transformed=np.fft.fft(wave_data[0])
d=int(len(transformed)/2)
while freq[d]>4000:
d-=10
freq=freq[:d]
transformed=transformed[:d]
for i,data in enumerate(transformed):
transformed[i]=abs(data)
return freq, transformed得到的结果
之后，为了进一步得到语谱图结果，采用如下代码，帧长为20ms，帧移为10ms。测试语音只保留3s内的信息，显示的频率范围是【0，7.5KHz】,之后的频率范围内的特征值被舍弃。
import numpy, wave
import numpy, matplotlib.pyplot as plt
# target: gain spec from framename
# input: filename, wav file path, string
# window_length_ms(/ms),window length(/ms), int
# window_shift_times(),rate of shit length, float
def getSpectrum(filename, window_length_ms, window_shift_times):
# read data
wav_file = wave.open(filename, 'r')
params = wav_file.getparams()
# nchannels, channel number (like, 2 channel wav)
# sampwidth, sample percision rate (like, 2)
# framerate, sample rate, (like, 44100)
# wav_length, how much points after sampled, (int)
nchannels, sampwidth, framerate, wav_length = params[:4]
str_data = wav_file.readframes(wav_length)
wave_data = numpy.fromstring(str_data, dtype=numpy.short)
wav_file.close()
# gain log spectrogram
window_length = framerate * window_length_ms / 1000 # change time to points number
window_shift = int(window_length * window_shift_times) # change time to points number
nframe = (wav_length - (window_length - window_shift)) / window_shift # gain frame number
spec = numpy.zeros((window_length/2, nframe)) # store spectrogram [only half part]
for i in xrange(nframe):
start = i * window_shift
end = start + window_length
spec[:, i] = numpy.log(numpy.abs(numpy.fft.fft(wave_data[start:end])))[:window_length/2]
return spec
# main process
speech_spectrum = getSpectrum('1.wav', 20, 0.5)
plt.imshow(speech_spectrum[:,:])
plt.xlim(0, 300)
plt.ylim(0, 150)
plt.show()得到的语谱图结果：
