6

我正在尝试使用Superpowered SDK对正在播放和同时录制的 mp3 文件应用实时时间拉伸和音高转换。问题是无论我做什么，输出的声音质量都很糟糕（到了失真的地步）。
我怀疑这是由于每个帧号的样本冲突。这是我的 cpp 文件的完整源代码：

static SuperpoweredAndroidAudioIO *audioIO;
static SuperpoweredTimeStretching *stretching;
static SuperpoweredAudiopointerList *outputBuffers;
static SuperpoweredDecoder *decoder;
static SuperpoweredRecorder *recorder;
const char *outFilePath;
const char *tempFilePath;

static short int *intBuffer;
static float *playerBuffer;

bool audioInitialized = false;
bool playing = false;

static bool audioProcessing(
        void *__unused clientData, // custom pointer
        short int *audio,           // buffer of interleaved samples
        int numberOfFrames,         // number of frames to process
        int __unused sampleRate     // sampling rate
) {

    if (playing) {
        unsigned int samplesDecoded = decoder->samplesPerFrame;
        if (decoder->decode(intBuffer, &samplesDecoded) == SUPERPOWEREDDECODER_ERROR) return false;
        if (samplesDecoded < 1) {
            playing = false;
            return false;
        }



        SuperpoweredAudiobufferlistElement inputBuffer;
        inputBuffer.samplePosition = decoder->samplePosition;
        inputBuffer.startSample = 0;
        inputBuffer.samplesUsed = 0;
        inputBuffer.endSample = samplesDecoded;
        inputBuffer.buffers[0] = SuperpoweredAudiobufferPool::getBuffer(samplesDecoded * 8 + 64);
        inputBuffer.buffers[1] = inputBuffer.buffers[2] = inputBuffer.buffers[3] = NULL;


        SuperpoweredShortIntToFloat(intBuffer, (float *) inputBuffer.buffers[0], samplesDecoded);

        stretching->process(&inputBuffer, outputBuffers);

        if (outputBuffers->makeSlice(0, outputBuffers->sampleLength)) {

            while (true) { 
                int numSamples = 0;
                float *timeStretchedAudio = (float *) outputBuffers->nextSliceItem(&numSamples);
                if (!timeStretchedAudio) break;

                SuperpoweredFloatToShortInt(timeStretchedAudio, intBuffer,
                                            (unsigned int) numSamples);
                SuperpoweredShortIntToFloat(intBuffer, playerBuffer, (unsigned int) numSamples);

                recorder->process(playerBuffer, (unsigned int) numSamples);
                SuperpoweredFloatToShortInt(playerBuffer, audio, (unsigned int) numSamples);

            };
            outputBuffers->clear();
            return true;
        };
    }
    return false;
}


extern "C" JNIEXPORT void
Java_com_example_activities_DubsmashActivity_InitAudio(
        JNIEnv  __unused *env,
        jobject  __unused obj,
        jint bufferSize,
        jint sampleRate,
        jstring outputPath,
        jstring tempPath
) {

    decoder = new SuperpoweredDecoder();

    outputBuffers = new SuperpoweredAudiopointerList(8, 16);

    outFilePath = env->GetStringUTFChars(outputPath, 0);
    tempFilePath = env->GetStringUTFChars(tempPath, 0);

}

extern "C" JNIEXPORT jdouble
Java_com_example_activities_DubsmashActivity_OpenFile(
        JNIEnv *env,
        jobject  __unused obj,
        jstring filePath) {
    const char *path = env->GetStringUTFChars(filePath, 0);
    decoder->open(path);
    intBuffer = (short int *) malloc(decoder->samplesPerFrame * 2 * sizeof(short int) + 32768);
    playerBuffer = (float *) malloc(decoder->samplesPerFrame * 2 * sizeof(short int) + 32768);
    audioIO = new SuperpoweredAndroidAudioIO(
            decoder->samplerate,
            decoder->samplesPerFrame,
            false,
            true,
            audioProcessing,
            NULL,
            -1, -1,
            decoder->samplesPerFrame * 2
    );

    stretching = new SuperpoweredTimeStretching(decoder->samplerate);

    stretching->setRateAndPitchShift(1, 0);

    recorder = new SuperpoweredRecorder(
            tempFilePath,              
            decoder->samplerate,  
            1,                  
            2,                  
            false,             
            recorderStopped,    
            NULL               
    );

    return 0;
}

需要考虑的一些注意事项：

  1. 这不是这个问题的重复，因为该线程中的解决方案对我不起作用
  2. 我试过玩decoder->samplesPerFrameandnumSamples但我不能得到一个像样的输出。
  3. 如果我将 Time Stretching1和 Pitch Shift 设置0为声音播放无缝。

更新 1：
经过更多的篡改和使用不同的样本数量值后，我认为问题一定出在音频输出 ( DAC MAN ) 期望的样本数量与outputBuffers->nextSliceItem实际提供的数量之间的差异。
话虽如此，我可以想出一种方法来缓解这个问题，那就是将输出附加outputBuffers->nextSliceItem到一个临时缓冲区，然后当它达到阈值时，将其定向到音频输出。

因此我的第二个问题是：C++ 中有没有办法将缓冲区附加到另一个缓冲区？

4

1 回答 1

3

您需要输出 audioProcessing(int numberOfFrames) 帧数。因此，在 outputBuffers->makeSlice 中，您需要询问 numberOfFrames，而不是 outputBuffers->sampleLength（基本上您要询问“outputBuffers 中的任意数量的帧”，而不是“numberOfFrames”）。

然后你从float转换为int，然后再转换回float？这没有意义。您在 timeStretchedAudio 中获得了浮点音频，可以立即由您的录音机处理。

之后，您将一些浮点样本转换为“音频”后，您忘记了前进。

最后，您从 outputBuffers 中删除所有音频，而您只需要删除输出到“音频”的帧数。

于 2018-10-26T06:35:15.137 回答