Question

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


def stft(sig, frameSize, overlapFac=0.5, window=np.hanning):
    win = window(frameSize)
    hopSize = int(frameSize - np.floor(overlapFac * frameSize))


    samples = np.append(np.zeros(np.floor(frameSize/2.0)), sig)    

    cols = np.ceil( (len(samples) - frameSize) / float(hopSize)) + 1

samples = np.append(samples, np.zeros(frameSize))

frames = stride_tricks.as_strided(samples, shape=(cols, frameSize), strides=(samples.strides[0]*hopSize, samples.strides[0])).copy()
frames *= win

return np.fft.rfft(frames)    


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))


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[:,scale[i]:], axis=1)
    else:        
        newspec[:,i] = np.sum(spec[:,scale[i]:scale[i+1]], axis=1)


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[scale[i]:])]
    else:
        freqs += [np.mean(allfreqs[scale[i]:scale[i+1]])]

return newspec, freqs


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)

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()

plotstft("wav1.wav")

有没有人可以帮我解决这个问题....真的很困惑......，当我尝试读取wave文件时发生了这个错误。是什么导致了这个，波形文件还是？我只是音频分析的初学者......真的需要一些帮助

Answer 1

WAV和PCM不完全相同，两者都是无损的，但是Wav是Windows友好文件，PCM是纯原始音频数据。尝试使用PCM文件。

我有同样的问题，BTW。我从wav切换到pcm并且它有效。

ValueError（“Incomplete wav chunk。”）ValueError：不完整的wav块

1 个答案: