wave

example-01

​import wave
wav = wave.open(‘A.wave’,"rb") # 單通道，時長約8秒  124800.0/16000 = 7.8
num_frame = wav.getnframes() # 	124800
num_channel=wav.getnchannels() # 1
framerate=wav.getframerate() # 16000
num_sample_width=wav.getsampwidth() # 獲取實例的比特寬度，每一幀的字節數2
str_data = wav.readframes(num_frame) # b'9\xff\x17\xff\n\xff\x1a\xffN\xffd\xffj...'
print(len(str_data)) # 249600 = 124800 * 2
wav.close() # 關閉流
wave_data = np.fromstring(str_data, dtype = np.short)#[-199,-233,...],長度(124800,)
wave_data.shape = -1, num_channel​

import numpy as np
import scipy.io.wavfile as wav
from python_speech_features import mfcc
def compute_mfcc(file):
	fs, audio = wav.read(file)
	mfcc_feat = mfcc(audio, samplerate=fs,numcep=26)
	print(mfcc_feat.shape,audio.shape)
	mfcc_feat = mfcc_feat[::3]
	print(mfcc_feat.shape)
	mfcc_feat = np.transpose(mfcc_feat)
	print(mfcc_feat.shape)
	return mfcc_feat
compute_mfcc("./tools/TX_aiplat/data/0004.wav")

輸出結果：
(799,26)
(267,26)
(26,267)

example-02

import numpy as np
from matplotlib import pyplot as plt
import scipy.io.wavfile as wav
from numpy.lib import stride_tricks

""" short time fourier transform of audio signal """
def stft(sig, frameSize, overlapFac=0.5, window=np.hanning):
    win = window(frameSize)
    hopSize = int(frameSize - np.floor(overlapFac * frameSize))
    # zeros at beginning (thus center of 1st window should be for sample nr. 0)   
    samples = np.append(np.zeros(int(np.floor(frameSize/2.0))), sig)    
    # cols for windowing
    cols = np.ceil( (len(samples) - frameSize) / float(hopSize)) + 1
    # zeros at end (thus samples can be fully covered by frames)
    samples = np.append(samples, np.zeros(frameSize))
    frames = stride_tricks.as_strided(samples, shape=(int(cols), frameSize), strides=(samples.strides[0]*hopSize, samples.strides[0])).copy()
    frames *= win

    return np.fft.rfft(frames)    

""" scale frequency axis logarithmically """    
def logscale_spec(spec, sr=44100, factor=20.):
    timebins, freqbins = np.shape(spec)
    scale = np.linspace(0, 1, freqbins) ** factor
    scale *= (freqbins-1)/max(scale)
    scale = np.unique(np.round(scale))

    # create spectrogram with new freq bins
    newspec = np.complex128(np.zeros([timebins, len(scale)]))
    for i in range(0, len(scale)):        
        if i == len(scale)-1:
            newspec[:,i] = np.sum(spec[:,int(scale[i]):], axis=1)
        else:        
            newspec[:,i] = np.sum(spec[:,int(scale[i]):int(scale[i+1])], axis=1)

    # list center freq of bins
    allfreqs = np.abs(np.fft.fftfreq(freqbins*2, 1./sr)[:freqbins+1])
    freqs = []
    for i in range(0, len(scale)):
        if i == len(scale)-1:
            freqs += [np.mean(allfreqs[int(scale[i]):])]
        else:
            freqs += [np.mean(allfreqs[int(scale[i]):int(scale[i+1])])]
    return newspec, freqs

""" plot spectrogram"""
def plotstft(audiopath, binsize=2**10, plotpath=None, colormap="jet"):
    samplerate, samples = wav.read(audiopath)
    s = stft(samples, binsize)
    sshow, freq = logscale_spec(s, factor=1.0, sr=samplerate)
    ims = 20.*np.log10(np.abs(sshow)/10e-6) # amplitude to decibel
    timebins, freqbins = np.shape(ims)
    print("timebins: ", timebins)
    print("freqbins: ", freqbins)
    plt.figure(figsize=(15, 7.5))
    plt.imshow(np.transpose(ims), origin="lower", aspect="auto", cmap=colormap, interpolation="none")
    plt.colorbar()

    plt.xlabel("time (s)")
    plt.ylabel("frequency (hz)")
    plt.xlim([0, timebins-1])
    plt.ylim([0, freqbins])
    xlocs = np.float32(np.linspace(0, timebins-1, 5))
    plt.xticks(xlocs, ["%.02f" % l for l in ((xlocs*len(samples)/timebins)+(0.5*binsize))/samplerate])
    ylocs = np.int16(np.round(np.linspace(0, freqbins-1, 10)))
    plt.yticks(ylocs, ["%.02f" % freq[i] for i in ylocs])
    if plotpath:
        plt.savefig(plotpath, bbox_inches="tight")
    else:
        plt.show()
    plt.clf()
    return ims
ims = plotstft("./1-1.wav")

import os
import wave
import pylab
def graph_spectrogram(wav_file):
    sound_info, frame_rate = get_wav_info(wav_file)
    pylab.figure(num=None, figsize=(19, 12))
    pylab.subplot(111)
    pylab.title('spectrogram of %r' % wav_file)
    pylab.specgram(sound_info, Fs=frame_rate)
    pylab.savefig('spectrogram.png')
def get_wav_info(wav_file):
    wav = wave.open(wav_file, 'r')
    frames = wav.readframes(-1)
    sound_info = pylab.fromstring(frames, 'int16')
    frame_rate = wav.getframerate()
    wav.close()
    return sound_info, frame_rate