data.py 文件源码

def _augment_speech(mfcc):

    # random frequency shift ( == speed perturbation effect on MFCC )
    r = np.random.randint(-2, 2)

    # shifting mfcc
    mfcc = np.roll(mfcc, r, axis=0)

    # zero padding
    if r > 0:
        mfcc[:r, :] = 0
    elif r < 0:
        mfcc[r:, :] = 0

    return mfcc


# Speech Corpus