preproccess.py 文件源码

def prepossessingAudio(audioPath, ppFilePath):
    print 'Prepossessing ' + audioPath

    featuresArray = []
    for i in range(0, SOUND_SAMPLE_LENGTH, HAMMING_STRIDE):
        if i + HAMMING_SIZE <= SOUND_SAMPLE_LENGTH - 1:
            y, sr = librosa.load(audioPath, offset=i / 1000.0, duration=HAMMING_SIZE / 1000.0)

            # Let's make and display a mel-scaled power (energy-squared) spectrogram
            S = librosa.feature.melspectrogram(y, sr=sr, n_mels=128)

            # Convert to log scale (dB). We'll use the peak power as reference.
            log_S = librosa.logamplitude(S, ref_power=np.max)

            mfcc = librosa.feature.mfcc(S=log_S, sr=sr, n_mfcc=13)
            featuresArray.append(mfcc)

            # featuresArray.append(S)

            if len(featuresArray) == 599:
                break

    print 'storing pp file: ' + ppFilePath

    f = open(ppFilePath, 'w')
    f.write(pickle.dumps(featuresArray))
    f.close()