cochleagram_extractor.py 文件源码

def cochleagram_extractor(xx, sr, win_len, shift_len, channel_number, win_type):
    fcoefs, f = make_erb_filters(sr, channel_number, 50)
    fcoefs = np.flipud(fcoefs)
    xf = erb_frilter_bank(xx, fcoefs)

    if win_type == 'hanning':
        window = np.hanning(channel_number)
    elif win_type == 'hamming':
        window = np.hamming(channel_number)
    elif win_type == 'triangle':
        window = (1 - (np.abs(channel_number - 1 - 2 * np.arange(1, channel_number + 1, 1)) / (channel_number + 1)))
    else:
        window = np.ones(channel_number)
    window = window.reshape((channel_number, 1))

    xe = np.power(xf, 2.0)
    frames = 1 + ((np.size(xe, 1)-win_len) // shift_len)
    cochleagram = np.zeros((channel_number, frames))
    for i in range(frames):
        one_frame = np.multiply(xe[:, i*shift_len:i*shift_len+win_len], np.repeat(window, win_len, 1))
        cochleagram[:, i] = np.sqrt(np.mean(one_frame, 1))

    cochleagram = np.where(cochleagram == 0.0, np.finfo(float).eps, cochleagram)
    return cochleagram