audio_tools.py 文件源码

def dct_compress(X, n_components, window_size=128):
    """
    Compress using the DCT

    Parameters
    ----------
    X : ndarray, shape=(n_samples,)
        The input signal to compress. Should be 1-dimensional

    n_components : int
        The number of DCT components to keep. Setting n_components to about
        .5 * window_size can give compression with fairly good reconstruction.

    window_size : int
        The input X is broken into windows of window_size, each of which are
        then compressed with the DCT.

    Returns
    -------
    X_compressed : ndarray, shape=(num_windows, window_size)
       A 2D array of non-overlapping DCT coefficients. For use with uncompress

    Reference
    ---------
    http://nbviewer.ipython.org/github/craffel/crucialpython/blob/master/week3/stride_tricks.ipynb
    """
    if len(X) % window_size != 0:
        append = np.zeros((window_size - len(X) % window_size))
        X = np.hstack((X, append))
    num_frames = len(X) // window_size
    X_strided = X.reshape((num_frames, window_size))
    X_dct = fftpack.dct(X_strided, norm='ortho')
    if n_components is not None:
        X_dct = X_dct[:, :n_components]
    return X_dct