audio_tools.py 文件源码

def overlap_dct_compress(X, n_components, window_size):
    """
    Overlap (at 50% of window_size) and compress X.

    Parameters
    ----------
    X : ndarray, shape=(n_samples,)
        Input signal to compress

    n_components : int
        number of DCT components to keep

    window_size : int
        Size of windows to take

    Returns
    -------
    X_dct : ndarray, shape=(n_windows, n_components)
        Windowed and compressed version of X
    """
    X_strided = halfoverlap(X, 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


# Evil voice is caused by adding double the zeros before inverse DCT...
# Very cool bug but makes sense