ios - 无输出的实时音频处理

Question

我在看这个例子http://teragonaudio.com/article/How-to-do-realtime-recording-with-effect-processing-on-iOS.html

我想关闭我的输出。我尝试将:kAudioSessionCategory_PlayAndRecord 更改为 kAudioSessionCategory_RecordAudio 但这不起作用。我也尝试摆脱:

  if(AudioUnitSetProperty(*audioUnit, kAudioUnitProperty_StreamFormat,
                            kAudioUnitScope_Output, 1, &streamDescription, sizeof(streamDescription)) != noErr) {
        return 1;
    }

因为我想从麦克风中获取声音而不是播放它。但是无论我做什么，当我的声音到达 renderCallback 方法时都会出现 -50 错误。当音频在输出上自动播放时，一切正常......

更新代码:

using namespace std;

AudioUnit *audioUnit = NULL;

float *convertedSampleBuffer = NULL;

int initAudioSession() {
    audioUnit = (AudioUnit*)malloc(sizeof(AudioUnit));

    if(AudioSessionInitialize(NULL, NULL, NULL, NULL) != noErr) {
        return 1;
    }

    if(AudioSessionSetActive(true) != noErr) {
        return 1;
    }

    UInt32 sessionCategory = kAudioSessionCategory_PlayAndRecord;
    if(AudioSessionSetProperty(kAudioSessionProperty_AudioCategory,
                               sizeof(UInt32), &sessionCategory) != noErr) {
        return 1;
    }

    Float32 bufferSizeInSec = 0.02f;
    if(AudioSessionSetProperty(kAudioSessionProperty_PreferredHardwareIOBufferDuration,
                               sizeof(Float32), &bufferSizeInSec) != noErr) {
        return 1;
    }

    UInt32 overrideCategory = 1;
    if(AudioSessionSetProperty(kAudioSessionProperty_OverrideCategoryDefaultToSpeaker,
                               sizeof(UInt32), &overrideCategory) != noErr) {
        return 1;
    }

    // There are many properties you might want to provide callback functions for:
    // kAudioSessionProperty_AudioRouteChange
    // kAudioSessionProperty_OverrideCategoryEnableBluetoothInput
    // etc.

    return 0;
}

OSStatus renderCallback(void *userData, AudioUnitRenderActionFlags *actionFlags,
                        const AudioTimeStamp *audioTimeStamp, UInt32 busNumber,
                        UInt32 numFrames, AudioBufferList *buffers) {
    OSStatus status = AudioUnitRender(*audioUnit, actionFlags, audioTimeStamp,
                                      1, numFrames, buffers);

    int doOutput = 0;

    if(status != noErr) {
        return status;
    }

    if(convertedSampleBuffer == NULL) {
        // Lazy initialization of this buffer is necessary because we don't
        // know the frame count until the first callback
        convertedSampleBuffer = (float*)malloc(sizeof(float) * numFrames);
        baseTime = (float)QRealTimer::getUptimeInMilliseconds();
    }

    SInt16 *inputFrames = (SInt16*)(buffers->mBuffers->mData);

    // If your DSP code can use integers, then don't bother converting to
    // floats here, as it just wastes CPU. However, most DSP algorithms rely
    // on floating point, and this is especially true if you are porting a
    // VST/AU to iOS.

    int i;

    for( i = numFrames; i < fftlength; i++ )        // Shifting buffer
        x_inbuf[i - numFrames] = x_inbuf[i];

    for(  i = 0; i < numFrames; i++) {
        x_inbuf[i + x_phase] = (float)inputFrames[i] / (float)32768;
    }

    if( x_phase + numFrames == fftlength )
    {
        x_alignment.SigProc_frontend(x_inbuf);  // Signal processing front-end (FFT!)
        doOutput = x_alignment.Align();


        /// Output as text! In the real-time version,
        //      this is where we update visualisation callbacks and launch other services
        if ((doOutput) & (x_netscore.isEvent(x_alignment.Position()))
            &(x_alignment.lastAction()<x_alignment.Position()) )
        {
          //  here i want to do something with my input!
        }
    }
    else
        x_phase += numFrames;


   return noErr;
}


int initAudioStreams(AudioUnit *audioUnit) {
    UInt32 audioCategory = kAudioSessionCategory_PlayAndRecord;
    if(AudioSessionSetProperty(kAudioSessionProperty_AudioCategory,
                               sizeof(UInt32), &audioCategory) != noErr) {
        return 1;
    }

    UInt32 overrideCategory = 1;
    if(AudioSessionSetProperty(kAudioSessionProperty_OverrideCategoryDefaultToSpeaker,
                               sizeof(UInt32), &overrideCategory) != noErr) {
        // Less serious error, but you may want to handle it and bail here
    }

    AudioComponentDescription componentDescription;
    componentDescription.componentType = kAudioUnitType_Output;
    componentDescription.componentSubType = kAudioUnitSubType_RemoteIO;
    componentDescription.componentManufacturer = kAudioUnitManufacturer_Apple;
    componentDescription.componentFlags = 0;
    componentDescription.componentFlagsMask = 0;
    AudioComponent component = AudioComponentFindNext(NULL, &componentDescription);
    if(AudioComponentInstanceNew(component, audioUnit) != noErr) {
        return 1;
    }

    UInt32 enable = 1;
    if(AudioUnitSetProperty(*audioUnit, kAudioOutputUnitProperty_EnableIO,
                            kAudioUnitScope_Input, 1, &enable, sizeof(UInt32)) != noErr) {
        return 1;
    }

    AURenderCallbackStruct callbackStruct;
    callbackStruct.inputProc = renderCallback; // Render function
    callbackStruct.inputProcRefCon = NULL;
    if(AudioUnitSetProperty(*audioUnit, kAudioUnitProperty_SetRenderCallback,
                            kAudioUnitScope_Input, 0, &callbackStruct,
                            sizeof(AURenderCallbackStruct)) != noErr) {
        return 1;
    }

    AudioStreamBasicDescription streamDescription;
    // You might want to replace this with a different value, but keep in mind that the
    // iPhone does not support all sample rates. 8kHz, 22kHz, and 44.1kHz should all work.
    streamDescription.mSampleRate = 44100;
    // Yes, I know you probably want floating point samples, but the iPhone isn't going
    // to give you floating point data. You'll need to make the conversion by hand from
    // linear PCM <-> float.
    streamDescription.mFormatID = kAudioFormatLinearPCM;
    // This part is important!
    streamDescription.mFormatFlags = kAudioFormatFlagIsSignedInteger |
    kAudioFormatFlagsNativeEndian |
    kAudioFormatFlagIsPacked;
    streamDescription.mBitsPerChannel = 16;
    // 1 sample per frame, will always be 2 as long as 16-bit samples are being used
    streamDescription.mBytesPerFrame = 2;
    streamDescription.mChannelsPerFrame = 1;
    streamDescription.mBytesPerPacket = streamDescription.mBytesPerFrame *
    streamDescription.mChannelsPerFrame;
    // Always should be set to 1
    streamDescription.mFramesPerPacket = 1;
    // Always set to 0, just to be sure
    streamDescription.mReserved = 0;

    // Set up input stream with above properties
    if(AudioUnitSetProperty(*audioUnit, kAudioUnitProperty_StreamFormat,
                            kAudioUnitScope_Input, 0, &streamDescription, sizeof(streamDescription)) != noErr) {
        return 1;
    }

    // Ditto for the output stream, which we will be sending the processed audio to
    if(AudioUnitSetProperty(*audioUnit, kAudioUnitProperty_StreamFormat,
                            kAudioUnitScope_Output, 1, &streamDescription, sizeof(streamDescription)) != noErr) {
        return 1;
    }

    return 0;
}


int startAudioUnit(AudioUnit *audioUnit) {
    if(AudioUnitInitialize(*audioUnit) != noErr) {
        return 1;
    }

    if(AudioOutputUnitStart(*audioUnit) != noErr) {
        return 1;
    }

    return 0;
}

然后从我的 VC 打电话:

  initAudioSession();
    initAudioStreams( audioUnit);
    startAudioUnit( audioUnit);

Answer 1

如果你只想录制，不想播放，只需注释掉设置 renderCallback 的行:

AURenderCallbackStruct callbackStruct;
callbackStruct.inputProc = renderCallback; // Render function
callbackStruct.inputProcRefCon = NULL;
if(AudioUnitSetProperty(*audioUnit, kAudioUnitProperty_SetRenderCallback,
   kAudioUnitScope_Input, 0, &callbackStruct,
   sizeof(AURenderCallbackStruct)) != noErr) {
  return 1;
}

看到代码后更新:

正如我所怀疑的，您缺少输入回调。添加这些行:

// at top:
#define kInputBus 1

AURenderCallbackStruct callbackStruct;
/**/
callbackStruct.inputProc = &ALAudioUnit::recordingCallback;
callbackStruct.inputProcRefCon = this;
status = AudioUnitSetProperty(audioUnit,
                              kAudioOutputUnitProperty_SetInputCallback,
                              kAudioUnitScope_Global,
                              kInputBus,
                              &callbackStruct,
                              sizeof(callbackStruct));

现在在你的 recordingCallback 中:

OSStatus ALAudioUnit::recordingCallback(void *inRefCon,
                                        AudioUnitRenderActionFlags *ioActionFlags,
                                        const AudioTimeStamp *inTimeStamp,
                                        UInt32 inBusNumber,
                                        UInt32 inNumberFrames,
                                        AudioBufferList *ioData)
{
    // TODO: Use inRefCon to access our interface object to do stuff
    // Then, use inNumberFrames to figure out how much data is available, and make
    // that much space available in buffers in an AudioBufferList.

    // Then:
    // Obtain recorded samples

    OSStatus status;

    ALAudioUnit *pThis = reinterpret_cast<ALAudioUnit*>(inRefCon);
    if (!pThis)
        return noErr;

    //assert (pThis->m_nMaxSliceFrames >= inNumberFrames);

    pThis->recorderBufferList->GetBufferList().mBuffers[0].mDataByteSize = inNumberFrames * pThis->m_recorderSBD.mBytesPerFrame;

    status = AudioUnitRender(pThis->audioUnit,
                             ioActionFlags,
                             inTimeStamp,
                             inBusNumber,
                             inNumberFrames,
                             &pThis->recorderBufferList->GetBufferList());
    THROW_EXCEPTION_IF_ERROR(status, "error rendering audio unit");

    // If we're not playing, I don't care about the data, simply discard it
    if (!pThis->playbackState || pThis->isSeeking) return noErr;

    // Now, we have the samples we just read sitting in buffers in bufferList
    pThis->DoStuffWithTheRecordedAudio(inNumberFrames, pThis->recorderBufferList, inTimeStamp);

    return noErr;
}

顺便说一句，我正在分配自己的缓冲区，而不是使用 AudioUnit 提供的缓冲区。如果您想使用 AudioUnit 分配的缓冲区，您可能想要更改这些部分。

更新:

如何分配自己的缓冲区:

recorderBufferList = new AUBufferList();
recorderBufferList->Allocate(m_recorderSBD, m_nMaxSliceFrames);
recorderBufferList->PrepareBuffer(m_recorderSBD, m_nMaxSliceFrames);

此外，如果您这样做，请告诉 AudioUnit 不要分配缓冲区:

// Disable buffer allocation for the recorder (optional - do this if we want to pass in our own)
flag = 0;
status = AudioUnitSetProperty(audioUnit,
                              kAudioUnitProperty_ShouldAllocateBuffer,
                              kAudioUnitScope_Input,
                              kInputBus,
                              &flag,
                              sizeof(flag));

您需要包含 CoreAudio utility classes