PortAudio 用于连续输入流的实时音频处理

Question

我正在使用 PortAudio 来实现实时音频处理。

我的主要任务是不断地从 mic 获取数据，并提供 100 个样本用于处理 (each FRAME = 100 samples at a time) 给其他一些处理线程。

这是我的回调，每次连续收集 100 个样本 -

static int paStreamCallback( const void* input, void* output,
    unsigned long samplesPerFrame,
    const PaStreamCallbackTimeInfo* timeInfo,
    PaStreamCallbackFlags statusFlags,
    void* userData ) {

    paTestData *data = (paTestData*) userData;
    const SAMPLE *readPtr = (const SAMPLE*)input;   // Casting input read to valid input type SAMPLE (float)
    unsigned long totalSamples = TOTAL_NUM_OF_SAMPLES ; // totalSamples = 100 here

    (void) output;
    (void) timeInfo;
    (void) statusFlags;

    static int count = 1;

    if(data->sampleIndex < count * samplesPerFrame){
        data->recordedSample[data->sampleIndex] = *readPtr;
        data->sampleIndex++;
    }

    else if(data->sampleIndex ==  count * samplesPerFrame){

        processSampleFrame(data->recordedSample);
        count++;
        finished = paContinue;
    }

    return finished;
}

我的`ma​​in函数-

int main(void){

// Some Code here

data.sampleIndex = 0;
data.frameIndex = 1;

numBytes = TOTAL_NUM_OF_SAMPLES * sizeof(SAMPLE);
data.recordedSample = (SAMPLE*)malloc(numBytes);

for(i=0; i < TOTAL_NUM_OF_SAMPLES; i++)
    data.recordedSample[i] = 0;

// Open Stream Initialization

err = Pa_StartStream(stream);

/* Recording audio here..Speak into the MIC */
printf("\nRecording...\n");
fflush(stdout);

while((err = Pa_IsStreamActive(stream)) == 1)
    Pa_Sleep(10);

    if(err < 0)
            goto done;

    err = Pa_CloseStream(stream);

// Some more code here
}

将每帧 100 个样本发送到 processSampleFrame。

void processSampleFrame(SAMPLE *singleFrame){

    // Free buffer of this frame
    // Processing sample frame here
}

挑战在于我需要实现一种方式，让processSampleFrame 处理样本的时间，我的callBack 应该处于活动状态并继续获取下一个Frame of 100 samples 并且（可能更多取决于处理时间processSampleFrame)。

此外，缓冲区应该能够在将帧传递给processSampleFrame 之前将其从帧中释放出来。

编辑 2：

我尝试使用PortAudio 提供的PaUtilRingBuffer 来实现。这是我的回调。

printf("Inside callback\n");
paTestData *data = (paTestData*) userData;

ring_buffer_size_t elementsWritable = PaUtil_GetRingBufferWriteAvailable(&data->ringBuffer);
ring_buffer_size_t elementsToWrite = rbs_min(elementsWritable, (ring_buffer_size_t)(samplesPerFrame * numChannels));

const SAMPLE *readPtr = (const SAMPLE*)input;
printf("Sample ReadPtr = %.8f\n", *readPtr);
(void) output;      // Preventing unused variable warnings
(void) timeInfo;
(void) statusFlags;

data->frameIndex += PaUtil_WriteRingBuffer(&data->ringBuffer, readPtr, elementsToWrite);

return paContinue;

和主要：

int main(void){

    paTestData data;    // Object of paTestData structure

    fflush(stdout);

    data.frameIndex = 1;

    long numBytes = TOTAL_NUM_OF_SAMPLES * LIMIT;
    data.ringBufferData = (SAMPLE*)PaUtil_AllocateMemory(numBytes);
    if(PaUtil_InitializeRingBuffer(&data.ringBuffer, sizeof(SAMPLE), ELEMENTS_TO_WRITE, data.ringBufferData) < 0){
        printf("Failed to initialise Ring Buffer.\n");
        goto done;

    err = Pa_StartStream(stream);

    /* Recording audio here..Speak into the MIC */
    printf("\nRecording samples\n");
    fflush(stdout);

    while((err = Pa_IsStreamActive(stream)) == 1)
        Pa_Sleep(10);

    if(err < 0)
                goto done;

        err = Pa_CloseStream(stream);

    // Error Handling here
}

PaTestData 结构：

typedef struct{

    SAMPLE *ringBufferData;
    PaUtilRingBuffer ringBuffer;    
    unsigned int frameIndex;
}
paTestData;

在成功获取分配的空间后，我面临同样的 seg-fault 问题，因为无法按照PortAudio 文档的建议在callback 中使用任何free。

在哪里可以释放分配给处理线程的已分配帧的缓冲区。可能是一种获得线程同步的方法在这里非常有用。感谢您的帮助。

Answer 1

处理音频输入的示例代码：

#define FRAME_SIZE                 1024
#define CIRCULAR_BUFFER_SIZE       (FRAME_SIZE * 4)

float buffer[CIRCULAR_BUFFER_SIZE];

typedef struct {
     int read, write;
     float vol;
} paData;

static int paStreamCallback(const void* input, void* output,
                            unsigned long samplesPerFrame,
                            const PaStreamCallbackTimeInfo* timeInfo,
                            PaStreamCallbackFlags statusFlags,
                            void* userData) {

    paData *data = (paData *)userData;
    // Write input buffer to our buffer: (memcpy function is fine, just a for loop of writing data
    memcpy(&buffer[write], input, samplesPerFrame); // Assuming samplesPerFrame = FRAME_SIZE

    // Increment write/wraparound
    write = (write + FRAME_SIZE) % CIRCULAR_BUFFER_SIZE;

    // dummy algorithm for processing blocks:
    processAlgorithm(&buffer[read]);

    // Write output
    float *dummy_buffer = &buffer[read]; // just for easy increment
    for (int i = 0; i < samplesPerFrame; i++) {
         // Mix audio input and processed input; 50% mix
         output[i] = input[i] * 0.5 + dummy_buffer[i] * 0.5;
    }

    // Increment read/wraparound
    read = (read + FRAME_SIZE) % CIRCULAR_BUFFER_SIZE;

    return paContinue;
}

int main(void) {
     // Initialize code here; any memory allocation needs to be done here! default buffers to 0 (silence)
     // initialize paData too; write = 0, read = 3072
     // read is 3072 because I'm thinking about this like a delay system.
}

把这个和一粒盐放在一起；显然更好的方法可以做到这一点，但它可以用作起点。