如何将 .wav 文件转换为 python3 中的频谱图
How to convert a .wav file to a spectrogram in python3
我正在尝试从 python3 中的 .wav 文件创建频谱图。
我希望最终保存的图像看起来类似于此图像：
我试过以下方法：
此堆栈溢出 post：
这个 post 有点奏效了。在 运行 之后，我得到了
但是，此图表不包含我需要的颜色。我需要一个有颜色的频谱图。我尝试修改此代码以尝试添加颜色，但是在花费大量时间和精力之后，我无法弄清楚！
然后我尝试了 this 教程。
当我尝试 运行 它并出现错误 TypeError: 'numpy.float64' object cannot be interpreted as an integer.
时，此代码崩溃（第 17 行）
第 17 行：
samples = np.append(np.zeros(np.floor(frameSize/2.0)), sig)
我试图通过强制转换来修复它
samples = int(np.append(np.zeros(np.floor(frameSize/2.0)), sig))
我也试过了
samples = np.append(np.zeros(int(np.floor(frameSize/2.0)), sig))
然而，这些最终都没有奏效。
我真的很想知道如何将我的 .wav 文件转换为带颜色的频谱图，以便我可以分析它们！任何帮助将不胜感激!!!!!
如果您希望我提供有关我的 python 版本、我尝试过的内容或我想要实现的目标的更多信息，请告诉我。
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()
在尝试执行此操作之前，请确保您的 wav 文件是单声道（单声道）而不是立体声（双声道）。我强烈建议阅读 scipy 文档，网址为 https://docs.scipy.org/doc/scipy-
0.19.0/reference/generated/scipy.signal.spectrogram.html.
将 plt.pcolormesh 放在 plt.imshow 之前似乎可以解决一些问题，正如@Davidjb 所指出的，如果出现解包错误，请按照下面@cgnorthcutt 的步骤操作。
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
对于 A Capella Science - Bohemian Gravity! 这给出：
使用graph_spectrogram(path_to_your_wav_file)。
我不记得我是从哪个博客截取这段代码的。每当我再次看到它时，我都会添加 link。
我已经修复了您在 http://www.frank-zalkow.de/en/code-snippets/create-audio-spectrograms-with-python.html
中遇到的错误
此实现更好，因为您可以更改 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)
您可以使用 librosa 来满足您的 mp3 频谱图需求。这是我找到的一些代码，感谢 Parul Pandey from medium。我使用的代码是这样的，
# Method described here
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！
上面初学者的回答非常好。我没有 50 rep，所以我不能对此发表评论，但如果你想要频域中的正确幅度，stft 函数应该如下所示：
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
我正在尝试从 python3 中的 .wav 文件创建频谱图。
我希望最终保存的图像看起来类似于此图像：
我试过以下方法：
此堆栈溢出 post：
这个 post 有点奏效了。在 运行 之后，我得到了
但是，此图表不包含我需要的颜色。我需要一个有颜色的频谱图。我尝试修改此代码以尝试添加颜色，但是在花费大量时间和精力之后，我无法弄清楚！
然后我尝试了 this 教程。
当我尝试 运行 它并出现错误 TypeError: 'numpy.float64' object cannot be interpreted as an integer.
时，此代码崩溃（第 17 行）第 17 行：
samples = np.append(np.zeros(np.floor(frameSize/2.0)), sig)
我试图通过强制转换来修复它
samples = int(np.append(np.zeros(np.floor(frameSize/2.0)), sig))
我也试过了
samples = np.append(np.zeros(int(np.floor(frameSize/2.0)), sig))
然而，这些最终都没有奏效。
我真的很想知道如何将我的 .wav 文件转换为带颜色的频谱图，以便我可以分析它们！任何帮助将不胜感激!!!!!
如果您希望我提供有关我的 python 版本、我尝试过的内容或我想要实现的目标的更多信息，请告诉我。
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()
在尝试执行此操作之前，请确保您的 wav 文件是单声道（单声道）而不是立体声（双声道）。我强烈建议阅读 scipy 文档，网址为 https://docs.scipy.org/doc/scipy- 0.19.0/reference/generated/scipy.signal.spectrogram.html.
将 plt.pcolormesh 放在 plt.imshow 之前似乎可以解决一些问题，正如@Davidjb 所指出的，如果出现解包错误，请按照下面@cgnorthcutt 的步骤操作。
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
对于 A Capella Science - Bohemian Gravity! 这给出：
使用graph_spectrogram(path_to_your_wav_file)。
我不记得我是从哪个博客截取这段代码的。每当我再次看到它时，我都会添加 link。
我已经修复了您在 http://www.frank-zalkow.de/en/code-snippets/create-audio-spectrograms-with-python.html
中遇到的错误
此实现更好，因为您可以更改 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)
您可以使用 librosa 来满足您的 mp3 频谱图需求。这是我找到的一些代码，感谢 Parul Pandey from medium。我使用的代码是这样的，
# Method described here
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！
上面初学者的回答非常好。我没有 50 rep，所以我不能对此发表评论，但如果你想要频域中的正确幅度，stft 函数应该如下所示：
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