为什么 MFCC 提取库 return 不同的值?

Why do MFCC extraction libs return different values?

我正在使用两个不同的库提取 MFCC 特征:

但是两者输出的结果不同,甚至形状也不一样。那是正常的吗?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)

你试过比较两者有一定的公差吗?我相信这两个 MFCC 是浮点数数组,测试是否完全相等可能并不明智。尝试使用具有一定公差的 numpy.testing.assert_allclose,然后确定公差是否足够好。

尽管如此,我想念你说的连形状都不匹配的问题,而且我没有 bob.ap 自信地对此发表评论的经验。但是,通常情况下,某些库出于窗口原因在输入数组的开头或结尾用零填充输入,如果其中一个库的处理方式不同,这可能是负责的。

However the output of the two is different and even the shapes are not the same. Is that normal?

是的,有不同的算法,每个实现选择自己的风格

or is there a parameter that I am missing?

这不仅仅是关于参数,还有算法上的差异,比如 window 形状(汉明与汉宁)、梅尔过滤器的形状、梅尔过滤器的开始、梅尔过滤器的归一化、提升、dct 风味和依此类推。

如果你想要相同的结果,只使用单个库进行提取,同步它们是非常无望的。