Python绘制音梅尔谱图像

import os
import matplotlib

matplotlib.use('Agg')  # No pictures displayed
import pylab
import librosa
import librosa.display
import numpy as np

sig, fs = librosa.load(os.path.join(os.path.dirname(os.path.realpath(__file__)), "video1.wav"))
# make pictures name
save_path = 'test.jpg'

# pylab.axis('off')  # no axis
# pylab.axes([0., 0., 1., 1.], frameon=False, xticks=[], yticks=[])  # Remove the white edge
S = librosa.feature.melspectrogram(y=sig, sr=fs)
librosa.display.specshow(librosa.power_to_db(S, ref=np.max),y_axis="mel", fmax=8000 * 1, x_axis="time")
pylab.savefig(save_path, bbox_inches=None, pad_inches=0)
pylab.close()

 原理解释：

02｜如何量化分析语音信号？-极客时间