base.py 文件源码

def mfccVTLP(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, alpha=1.0):
    """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.
    :returns: A numpy array of size (NUMFRAMES by numcep) containing features. Each row holds 1 feature vector.
    """
    feat,energy = fbankVTLP(signal,samplerate,winlen,winstep,nfilt,nfft,lowfreq,highfreq,preemph,False,alpha)
    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