Question

我正在尝试使用Superpowered SDK对正在播放并同时录制的mp3文件应用实时时间拉伸和音调转换。问题在于，无论我做什么，输出的声音质量都是糟糕的（以至于失真）。
我怀疑这是由于每个帧号的样本冲突造成的。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;
}

一些注意事项：

这不是this question的副本，因为该线程中的解决方案对我不起作用
我尝试过使用decoder->samplesPerFrame和numSamples，但我无法获得令人满意的输出。
如果我将“时间延伸”设置为1，而将“音高偏移”设置为0，则声音将无缝播放。

更新1：
经过更多的篡改并以不同的采样值值播放之后，我认为问题必然出在音频输出（DAC MAN）期望的采样数量与实际outputBuffers->nextSliceItem的采样数量之间提供。
话虽如此，我可以想到一种缓解此问题的方法，那就是将outputBuffers->nextSliceItem的输出附加到临时缓冲区，然后在达到阈值时将其定向到音频输出。

第二个问题：在C ++中是否可以将缓冲区追加到另一个缓冲区？

Answer 1

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（基本上是在询问“ outputBuffers中的任何帧数”，而不是“ numberOfFrames”）。

然后您从float转换为int，然后又转换回float？这没有道理。您在timeStretchedAudio中获得了浮点音频，录音机可以立即对其进行处理。

那之后，在将一些浮点样本转换为音频后，您忘了将“音频”向前移动。

最后，您从outputBuffers中删除了所有音频，而只需要删除输出为“音频”的帧数。

超级强大：无法使TimeStretching正常工作，输出声音失真

1 个答案: