mel_coefficients.py 文件源码

def mfcc(s,fs, nfiltbank):

    #divide into segments of 25 ms with overlap of 10ms
    nSamples = np.int32(0.025*fs)
    overlap = np.int32(0.01*fs)
    nFrames = np.int32(np.ceil(len(s)/(nSamples-overlap)))
    #zero padding to make signal length long enough to have nFrames
    padding = ((nSamples-overlap)*nFrames) - len(s)
    if padding > 0:
        signal = np.append(s, np.zeros(padding))
    else:
        signal = s
    segment = np.empty((nSamples, nFrames))
    start = 0
    for i in range(nFrames):
        segment[:,i] = signal[start:start+nSamples]
        start = (nSamples-overlap)*i

    #compute periodogram
    nfft = 512
    periodogram = np.empty((nFrames,nfft/2 + 1))
    for i in range(nFrames):
        x = segment[:,i] * hamming(nSamples)
        spectrum = fftshift(fft(x,nfft))
        periodogram[i,:] = abs(spectrum[nfft/2-1:])/nSamples

    #calculating mfccs    
    fbank = mel_filterbank(nfft, nfiltbank, fs)
    #nfiltbank MFCCs for each frame
    mel_coeff = np.empty((nfiltbank,nFrames))
    for i in range(nfiltbank):
        for k in range(nFrames):
            mel_coeff[i,k] = np.sum(periodogram[k,:]*fbank[:,i])

    mel_coeff = np.log10(mel_coeff)
    mel_coeff = dct(mel_coeff)
    #exclude 0th order coefficient (much larger than others)
    mel_coeff[0,:]= np.zeros(nFrames)
    return mel_coeff