python - 为什么 MFCC 提取库返回不同的值?
问题描述
我正在使用两个不同的库提取 MFCC 功能:
- python_speech_features 库
- BOB 库
但是两者的输出不同,甚至形状也不相同。这正常吗?还是我缺少一个参数?
我的代码的相关部分如下:
import bob.ap
import numpy as np
from scipy.io.wavfile import read
from sklearn import preprocessing
from python_speech_features import mfcc, delta, logfbank
def bob_extract_features(audio, rate):
#get MFCC
rate = 8000 # rate
win_length_ms = 30 # The window length of the cepstral analysis in milliseconds
win_shift_ms = 10 # The window shift of the cepstral analysis in milliseconds
n_filters = 26 # The number of filter bands
n_ceps = 13 # The number of cepstral coefficients
f_min = 0. # The minimal frequency of the filter bank
f_max = 4000. # The maximal frequency of the filter bank
delta_win = 2 # The integer delta value used for computing the first and second order derivatives
pre_emphasis_coef = 0.97 # The coefficient used for the pre-emphasis
dct_norm = True # A factor by which the cepstral coefficients are multiplied
mel_scale = True # Tell whether cepstral features are extracted on a linear (LFCC) or Mel (MFCC) scale
c = bob.ap.Ceps(rate, win_length_ms, win_shift_ms, n_filters, n_ceps, f_min,
f_max, delta_win, pre_emphasis_coef, mel_scale, dct_norm)
c.with_delta = False
c.with_delta_delta = False
c.with_energy = False
signal = np.cast['float'](audio) # vector should be in **float**
example_mfcc = c(signal) # mfcc + mfcc' + mfcc''
return example_mfcc
def psf_extract_features(audio, rate):
signal = np.cast['float'](audio) #vector should be in **float**
mfcc_feature = mfcc(signal, rate, winlen = 0.03, winstep = 0.01, numcep = 13,
nfilt = 26, nfft = 512,appendEnergy = False)
#mfcc_feature = preprocessing.scale(mfcc_feature)
deltas = delta(mfcc_feature, 2)
fbank_feat = logfbank(audio, rate)
combined = np.hstack((mfcc_feature, deltas))
return mfcc_feature
track = 'test-sample.wav'
rate, audio = read(track)
features1 = psf_extract_features(audio, rate)
features2 = bob_extract_features(audio, rate)
print("--------------------------------------------")
t = (features1 == features2)
print(t)
解决方案
您是否尝试过将两者进行比较?我相信这两个 MFCC 是浮点数数组,测试完全相等可能并不明智。尝试使用numpy.testing.assert_allclose
一些公差,并确定公差是否足够好。
尽管如此,我还是想念你说即使形状不匹配,我也没有使用 bob.ap 的经验来自信地对此发表评论。但是,通常情况下,出于窗口原因,某些库在输入数组的开头或结尾用零填充输入,如果其中一个以不同的方式执行,这可能是原因。
推荐阅读
- sql - 如何在一行中显示列名
- oop - 哪些 SOLID 和现代 OO 原则将受到影响,以及如果我们取消对关注点分离的坚持,又会如何?
- django - 控制 select_related
- machine-learning - Vowpal Wabbit:无法使用 gd_mf_weights 从经过训练的 --rank 模型中检索潜在因素
- react-native - 为什么没有显示来自“native-base”的图标
- python - 如何在就地修改属性时调用属性装饰器?
- javascript - AJAX/Spring MVC:在 POST 请求中以括号表示法呈现 JSON 对象
- javascript - 在 Promise 中转换 forEach(没有 ASYC/AWAIT 遗留代码)
- node.js - AWS cognito:adminUpdateUserAttributes 不起作用并且没有给出错误,我错过了什么吗?
- python-3.x - 从 RAM 中读取 .jpg