如何在python3中將.wav文件轉換為頻譜圖

Question

我正在嘗試從 python3 中的 .wav 文件創建頻譜圖。

我希望最終保存的圖像看起來類似於此圖像：

我嘗試了以下方法：

此堆棧溢出帖子： 波形文件的頻譜圖

這篇文章有點奏效。 運行后，我得到了

但是，此圖不包含我需要的顏色。 我需要一個有顏色的光譜圖。 我嘗試修改此代碼以嘗試添加顏色，但是在為此花費了大量時間和精力之后，我無法弄清楚！

然后我嘗試了這個教程。

當我嘗試運行它時，此代碼崩潰（在第 17 行），並出現錯誤 TypeError: 'numpy.float64' object cannot be interpret as an integer。

第 17 行：

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

我試圖通過鑄造來修復它

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

我也試過

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

然而，這些最終都沒有奏效。

我真的很想知道如何將我的 .wav 文件轉換為帶有顏色的頻譜圖，以便我可以分析它們！ 任何幫助，將不勝感激！！！！！

如果您希望我提供有關我的 Python 版本、我嘗試過的內容或我想要實現的內容的更多信息，請告訴我。

Answer 1

使用scipy.signal.spectrogram 。

import matplotlib.pyplot as plt
from scipy import signal
from scipy.io import wavfile

sample_rate, samples = wavfile.read('path-to-mono-audio-file.wav')
frequencies, times, spectrogram = signal.spectrogram(samples, sample_rate)

plt.pcolormesh(times, frequencies, spectrogram)
plt.imshow(spectrogram)
plt.ylabel('Frequency [Hz]')
plt.xlabel('Time [sec]')
plt.show()

在嘗試執行此操作之前，請確保您的 wav 文件是單聲道（單聲道）而不是立體聲（雙聲道）。 我強烈建議閱讀https://docs.scipy.org/doc/scipy-0.19.0/reference/generated/scipy.signal.spectrogram.html 上的 scipy 文檔。

plt.pcolormesh plt.imshow所指出的，將plt.pcolormesh放在plt.pcolormesh之前似乎可以解決一些問題，如果發生解包錯誤，請按照下面@cgnorthcutt 的步驟進行操作。

Answer 2

我已經修復了您在http://www.frank-zalkow.de/en/code-snippets/create-audio-spectrograms-with-python.html 中遇到的錯誤
這種實現更好，因為您可以更改binsize （例如binsize=2**8 ）

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(filepath)

Answer 3

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

對於卡佩拉科學 - 波西米亞重力！ 這給出：

使用graph_spectrogram(path_to_your_wav_file) 。 我不記得我從哪里獲取這個片段的博客。 每當我再次看到它時，我都會添加鏈接。

Answer 4

您可以使用librosa來滿足您的 mp3 librosa需求。 這是我找到的一些代碼，感謝來自 medium 的 Parul Pandey 。 我使用的代碼是這樣的

# Method described here https://stackoverflow.com/questions/15311853/plot-spectogram-from-mp3

import librosa
import librosa.display
from pydub import AudioSegment
import matplotlib.pyplot as plt
from scipy.io import wavfile
from tempfile import mktemp

def plot_mp3_matplot(filename):
    """
    plot_mp3_matplot -- using matplotlib to simply plot time vs amplitude waveplot
    
    Arguments:
    filename -- filepath to the file that you want to see the waveplot for
    
    Returns -- None
    """
    
    # sr is for 'sampling rate'
    # Feel free to adjust it
    x, sr = librosa.load(filename, sr=44100)
    plt.figure(figsize=(14, 5))
    librosa.display.waveplot(x, sr=sr)

def convert_audio_to_spectogram(filename):
    """
    convert_audio_to_spectogram -- using librosa to simply plot a spectogram
    
    Arguments:
    filename -- filepath to the file that you want to see the waveplot for
    
    Returns -- None
    """
    
    # sr == sampling rate 
    x, sr = librosa.load(filename, sr=44100)
    
    # stft is short time fourier transform
    X = librosa.stft(x)
    
    # convert the slices to amplitude
    Xdb = librosa.amplitude_to_db(abs(X))
    
    # ... and plot, magic!
    plt.figure(figsize=(14, 5))
    librosa.display.specshow(Xdb, sr = sr, x_axis = 'time', y_axis = 'hz')
    plt.colorbar()
    
# same as above, just changed the y_axis from hz to log in the display func    
def convert_audio_to_spectogram_log(filename):
    x, sr = librosa.load(filename, sr=44100)
    X = librosa.stft(x)
    Xdb = librosa.amplitude_to_db(abs(X))
    plt.figure(figsize=(14, 5))
    librosa.display.specshow(Xdb, sr = sr, x_axis = 'time', y_axis = 'log')
    plt.colorbar()    

干杯!

Answer 5

上面初學者的回答非常好。 我沒有 50 rep，所以我不能評論它，但如果你想要頻域中的正確幅度，stft 函數應該是這樣的：

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, 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
    
    fftResults = np.fft.rfft(frames)
    windowCorrection = 1/(np.sum(np.hanning(frameSize))/frameSize) #This is amplitude correct (1/mean(window)). Energy correction is 1/rms(window)
    FFTcorrection = 2/frameSize
    scaledFftResults = fftResults*windowCorrection*FFTcorrection

    return scaledFftResults