从声音文件中获取帧

Question

有谁知道如何将声音文件分割成帧，然后将这些帧转换成 numpy 数组，详细说明帧中的特定声音频率？

例如，使用 cv2，我可以将影片剪辑分成多个帧，然后可以将这些帧存储为图像库。这段代码很好地完成了工作，在一定程度上我可以轻松地获得每张图像的颜色直方图。

filepath1 = input('Please enter the filepath for where the frames should be saved: ') 

name = input('Please enter the name of the clip: ') 

ret, frame = clip.read()
count = 0
ret == True
while ret:
    ret, frame = clip.read()
    cv2.imwrite(os.path.join(filepath1,name+'%d.png'%count), frame)
    count += 1

但我似乎找不到任何与声音文件同等直接的东西；有人对如何（或是否）可以完成有任何建议吗？

Answer 1

严格来说，相当于电影帧的声音文件是音频样本。这只是每个通道的一个值，所以我不确定这是否是您真正想要的。我对你想要实现的目标的最佳猜测是分析文件的频率内容如何随时间变化。

也许你想看看 spectrogram? In this case, the following script taken from www.frank-zalkow.de 可能完全按照你的意愿行事，或者至少给你一些如何开始的想法。

#!/usr/bin/env python
#coding: utf-8
""" 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("my_audio_file.wav")

从声音文件中获取帧

Getting frame from soundfile

python

audio

numpy

wave