base.py 文件源码

def mfcc(signal, samplerate=16000, winlen=0.025, winstep=0.01, numcep=13,
         nfilt=26, nfft=512, lowfreq=0, highfreq=None, preemph=0.97, ceplifter=22, appendEnergy=True,
         winfunc=lambda x: numpy.ones((x, ))):
    """Compute MFCC features from an audio signal.

    :param signal: the audio signal from which to compute features. Should be an N*1 array
    :param samplerate: the samplerate of the signal we are working with.
    :param winlen: the length of the analysis window in seconds. Default is 0.025s (25 milliseconds)
    :param winstep: the step between successive windows in seconds. Default is 0.01s (10 milliseconds)
    :param numcep: the number of cepstrum to return,  default 13
    :param nfilt: the number of filters in the filterbank,  default 26.
    :param nfft: the FFT size. Default is 512.
    :param lowfreq: lowest band edge of mel filters. In Hz,  default is 0.
    :param highfreq: highest band edge of mel filters. In Hz,  default is samplerate/2
    :param preemph: apply preemphasis filter with preemph as coefficient. 0 is no filter. Default is 0.97.
    :param ceplifter: apply a lifter to final cepstral coefficients. 0 is no lifter. Default is 22.
    :param appendEnergy: if this is true,  the zeroth cepstral coefficient is replaced with the log of the total frame energy.
    :param winfunc: the analysis window to apply to each frame. By default no window is applied.
    :returns: A numpy array of size (NUMFRAMES by numcep) containing features. Each row holds 1 feature vector.
    """
    feat, energy = fbank(signal, samplerate, winlen, winstep, nfilt, nfft, lowfreq, highfreq, preemph, winfunc)
    feat = numpy.log(feat)
    feat = dct(feat,  type=2,  axis=1,  norm='ortho')[:, :numcep]
    feat = lifter(feat, ceplifter)
    if appendEnergy: feat[:, 0] = numpy.log(energy) # replace first cepstral coefficient with log of frame energy
    return feat