python - 如何使用python matplotlib库从WAV文件中提取数据？

Question

我试图从wav文件中提取数据，以便对每个频率及其幅度相对于时间的音频进行分析，我的目标是为大学项目的机器学习算法运行此数据，经过一番谷歌搜索之后，我发现这可以通过Python的matplotlib库完成，我看到一些示例代码运行了短傅里叶变换并绘制了这些wav文件的频谱图，但无法理解如何使用该库来提取数据(给定频率下所有频率的幅度时间在音频文件中)并将其存储在3D数组或.mat文件中。
这是我在website上看到的代码:

#!/usr/bin/env python

""" This work is licensed under a Creative Commons Attribution 3.0 Unported License.
Frank Zalkow, 2012-2013 """

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

    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("abc.wav")

请指导我了解如何提取数据，如果不是通过matplotlib提取数据，请向我推荐其他一些可以帮助我实现这一目标的库。

Answer 1

首先，这看起来像我的代码，该代码据称已获得CC许可。我不太认真，但是您不应该忽略这些方面(在这种情况下，您省略了作者身份的声明)，其他人可能会对这种事情感到更加iff贬。

给您的问题:在这段代码中，stft不是由matplotlib计算的，而是由numpy计算的。您可以这样获得:

samplerate, samples = wav.read(audiopath)
s = stft(samples, 1024)

我不确定为什么要3D阵列？它是一个2D数组，但是值很复杂。如果要将其保存在.mat文件中:

from scipy.io import savemat
savemat("file.mat", {'arr': s})