audio_eval.py 文件源码

def stft(sig, frameSize, overlapFac=0.75, window=np.hanning):
    """ short time fourier transform of audio signal """
    win = window(frameSize)
    hopSize = int(frameSize - np.floor(overlapFac * frameSize))
    # zeros at beginning (thus center of 1st window should be for sample nr. 0)
    # samples = np.append(np.zeros(np.floor(frameSize / 2.0)), sig)
    samples = np.array(sig, dtype='float64')
    # cols for windowing
    cols = np.ceil((len(samples) - frameSize) / float(hopSize)) + 1
    # zeros at end (thus samples can be fully covered by frames)
    # samples = np.append(samples, np.zeros(frameSize))
    frames = stride_tricks.as_strided(
        samples,
        shape=(cols, frameSize),
        strides=(samples.strides[0] * hopSize, samples.strides[0])).copy()
    frames *= win
    return np.fft.rfft(frames)


# all the definition of the flowing variable can be found
# train_net.py