audio_tools.py 文件源码

def xcorr_offset(x1, x2):
    """
    Under MSR-LA License

    Based on MATLAB implementation from Spectrogram Inversion Toolbox

    References
    ----------
    D. Griffin and J. Lim. Signal estimation from modified
    short-time Fourier transform. IEEE Trans. Acoust. Speech
    Signal Process., 32(2):236-243, 1984.

    Malcolm Slaney, Daniel Naar and Richard F. Lyon. Auditory
    Model Inversion for Sound Separation. Proc. IEEE-ICASSP,
    Adelaide, 1994, II.77-80.

    Xinglei Zhu, G. Beauregard, L. Wyse. Real-Time Signal
    Estimation from Modified Short-Time Fourier Transform
    Magnitude Spectra. IEEE Transactions on Audio Speech and
    Language Processing, 08/2007.
    """
    x1 = x1 - x1.mean()
    x2 = x2 - x2.mean()
    frame_size = len(x2)
    half = frame_size // 2
    corrs = np.convolve(x1.astype('float32'), x2[::-1].astype('float32'))
    corrs[:half] = -1E30
    corrs[-half:] = -1E30
    offset = corrs.argmax() - len(x1)
    return offset