ios - 设置效果 AudioUnit

Question

我正在尝试编写一个 iOS 应用程序，从麦克风捕获声音，将其通过高通滤波器，并对处理后的声音进行一些计算。基于 Stefan Popp 的 MicInput ( http://www.stefanpopp.de/2011/capture-iphone-microphone/ )，我试图在 I/O 音频单元的输入和输出之间放置一个效果音频单元(更具体地说，是一个高通滤波器效果单元)。设置上述 AU 后，当我在 I/O AU 的渲染回调中调用 AudioUnitRender(fxAudioUnit, ...) 时，会出现 10877 错误 (kAudioUnitErr_InvalidElement)。

AudioProcessingWithAudioUnitAPI.h

//
//  AudioProcessingWithAudioUnitAPI.h
//

#import <Foundation/Foundation.h>
#import <AudioToolbox/AudioToolbox.h>
#import <AVFoundation/AVAudioSession.h>

@interface AudioProcessingWithAudioUnitAPI : NSObject

@property (readonly) AudioBuffer                        audioBuffer;
@property (readonly) AudioComponentInstance             audioUnit;
@property (readonly) AudioComponentInstance             fxAudioUnit;

...

@end

AudioProcessingWithAudioUnitAPI.m

//
//  AudioProcessingWithAudioUnitAPI.m
//

#import "AudioProcessingWithAudioUnitAPI.h"

@implementation AudioProcessingWithAudioUnitAPI

@synthesize isPlaying = _isPlaying;
@synthesize outputLevelDisplay = _outputLevelDisplay;
@synthesize audioBuffer = _audioBuffer;
@synthesize audioUnit = _audioUnit;
@synthesize fxAudioUnit = _fxAudioUnit;

...

#pragma mark Recording callback

static OSStatus recordingCallback(void *inRefCon, 
                              AudioUnitRenderActionFlags *ioActionFlags, 
                              const AudioTimeStamp *inTimeStamp, 
                              UInt32 inBusNumber, 
                              UInt32 inNumberFrames, 
                              AudioBufferList *ioData) {

    // the data gets rendered here
    AudioBuffer buffer;

    // a variable where we check the status
    OSStatus status;

    /**
     This is the reference to the object who owns the callback.
     */
    AudioProcessingWithAudioUnitAPI *audioProcessor = (__bridge AudioProcessingWithAudioUnitAPI*) inRefCon;

    /**
     on this point we define the number of channels, which is mono
     for the iphone. the number of frames is usally 512 or 1024.
     */
    buffer.mDataByteSize = inNumberFrames * 2; // sample size
    buffer.mNumberChannels = 1; // one channel
    buffer.mData = malloc( inNumberFrames * 2 ); // buffer size

    // we put our buffer into a bufferlist array for rendering
    AudioBufferList bufferList;
    bufferList.mNumberBuffers = 1;
    bufferList.mBuffers[0] = buffer;

在接下来的 AudioUnitRender 调用中会抛出 10887 错误:

    status = AudioUnitRender([audioProcessor fxAudioUnit], ioActionFlags, inTimeStamp, inBusNumber, inNumberFrames, &bufferList);
[audioProcessor hasError:status:__FILE__:__LINE__];

...

// process the bufferlist in the audio processor
    [audioProcessor processBuffer:&bufferList];

    //do some further processing

    // clean up the buffer
    free(bufferList.mBuffers[0].mData);

    return noErr;
}

#pragma mark FX AudioUnit render callback
//This just asks for samples to the microphone (I/O AU render)
static OSStatus fxAudioUnitRenderCallback(void *inRefCon, 
                                      AudioUnitRenderActionFlags *ioActionFlags, 
                                      const AudioTimeStamp *inTimeStamp, 
                                      UInt32 inBusNumber, 
                                      UInt32 inNumberFrames, 
                                      AudioBufferList *ioData)
{
    OSStatus retorno;

    AudioProcessingWithAudioUnitAPI* audioProcessor = (__bridge AudioProcessingWithAudioUnitAPI*)inRefCon;

    retorno = AudioUnitRender([audioProcessor audioUnit],
                          ioActionFlags,
                          inTimeStamp,
                          inBusNumber,
                          inNumberFrames,
                          ioData);
    [audioProcessor hasError:retorno:__FILE__:__LINE__];

    return retorno;
}

#pragma mark Playback callback

static OSStatus playbackCallback(void *inRefCon, 
                             AudioUnitRenderActionFlags *ioActionFlags, 
                             const AudioTimeStamp *inTimeStamp, 
                             UInt32 inBusNumber, 
                             UInt32 inNumberFrames, 
                             AudioBufferList *ioData) {    

    /**
     This is the reference to the object who owns the callback.
     */
    AudioProcessingWithAudioUnitAPI *audioProcessor = (__bridge AudioProcessingWithAudioUnitAPI*) inRefCon;

    // iterate over incoming stream and copy to output stream
    for (int i=0; i < ioData->mNumberBuffers; i++) { 
        AudioBuffer buffer = ioData->mBuffers[i];

        // find minimum size
        UInt32 size = min(buffer.mDataByteSize, [audioProcessor audioBuffer].mDataByteSize);

        // copy buffer to audio buffer which gets played after function return
        memcpy(buffer.mData, [audioProcessor audioBuffer].mData, size);

        // set data size
        buffer.mDataByteSize = size; 
    }
    return noErr;
}

#pragma mark - objective-c class methods
-(AudioProcessingWithAudioUnitAPI*)init
{
    self = [super init];
    if (self) {
        self.isPlaying = NO;
        [self initializeAudio];
    }
    return self;
}

-(void)initializeAudio
{    
    OSStatus status;

    // We define the audio component
    AudioComponentDescription desc;
    desc.componentType = kAudioUnitType_Output; // we want to ouput
    desc.componentSubType = kAudioUnitSubType_RemoteIO; // we want in and ouput
    desc.componentFlags = 0; // must be zero
    desc.componentFlagsMask = 0; // must be zero
    desc.componentManufacturer = kAudioUnitManufacturer_Apple; // select provider

    // find the AU component by description
    AudioComponent component = AudioComponentFindNext(NULL, &desc);

    // create audio unit by component
    status = AudioComponentInstanceNew(component, &_audioUnit);

    [self hasError:status:__FILE__:__LINE__];

    // and now for the fx AudioUnit
        desc.componentType = kAudioUnitType_Effect;
    desc.componentSubType = kAudioUnitSubType_HighPassFilter;

    // find the AU component by description
    component = AudioComponentFindNext(NULL, &desc);

    // create audio unit by component
    status = AudioComponentInstanceNew(component, &_fxAudioUnit);

    [self hasError:status:__FILE__:__LINE__];

    // define that we want record io on the input bus
    AudioUnitElement inputElement = 1;
    AudioUnitElement outputElement = 0;

    UInt32 flag = 1;
    status = AudioUnitSetProperty(self.audioUnit, 
                              kAudioOutputUnitProperty_EnableIO, // use io
                              kAudioUnitScope_Input, // scope to input
                              inputElement, // select input bus (1)
                              &flag, // set flag
                              sizeof(flag));
    [self hasError:status:__FILE__:__LINE__];

    UInt32 anotherFlag = 0;
    // disable output (I don't want to hear back from the device)
    status = AudioUnitSetProperty(self.audioUnit, 
                              kAudioOutputUnitProperty_EnableIO, // use io
                              kAudioUnitScope_Output, // scope to output
                              outputElement, // select output bus (0)
                              &anotherFlag, // set flag
                              sizeof(flag));
    [self hasError:status:__FILE__:__LINE__];

    /* 
     We need to specify our format on which we want to work.
     We use Linear PCM cause its uncompressed and we work on raw data.
     for more informations check.

     We want 16 bits, 2 bytes per packet/frames at 44khz 
     */
    AudioStreamBasicDescription audioFormat;
    audioFormat.mSampleRate         = SAMPLE_RATE;
    audioFormat.mFormatID           = kAudioFormatLinearPCM;
    audioFormat.mFormatFlags        = kAudioFormatFlagIsPacked | kAudioFormatFlagIsSignedInteger;
    audioFormat.mFramesPerPacket    = 1;
    audioFormat.mChannelsPerFrame   = 1;
    audioFormat.mBitsPerChannel     = 16; //65536
    audioFormat.mBytesPerPacket     = 2;
    audioFormat.mBytesPerFrame      = 2;

    // set the format on the output stream
    status = AudioUnitSetProperty(self.audioUnit, 
                              kAudioUnitProperty_StreamFormat, 
                              kAudioUnitScope_Output, 
                              inputElement, 
                              &audioFormat, 
                              sizeof(audioFormat));

    [self hasError:status:__FILE__:__LINE__];

    // set the format on the input stream
    status = AudioUnitSetProperty(self.audioUnit, 
                              kAudioUnitProperty_StreamFormat, 
                              kAudioUnitScope_Input, 
                              outputElement, 
                              &audioFormat, 
                              sizeof(audioFormat));
    [self hasError:status:__FILE__:__LINE__];

    /**
     We need to define a callback structure which holds
     a pointer to the recordingCallback and a reference to
     the audio processor object
     */
    AURenderCallbackStruct callbackStruct;

    // set recording callback
    callbackStruct.inputProc = recordingCallback; // recordingCallback pointer
    callbackStruct.inputProcRefCon = (__bridge void*)self;

    // set input callback to recording callback on the input bus
    status = AudioUnitSetProperty(self.audioUnit, 
                              kAudioOutputUnitProperty_SetInputCallback, 
                              kAudioUnitScope_Global, 
                              inputElement, 
                              &callbackStruct, 
                              sizeof(callbackStruct));

    [self hasError:status:__FILE__:__LINE__];

    /*
     We do the same on the output stream to hear what is coming
     from the input stream
     */
    callbackStruct.inputProc = playbackCallback;
    callbackStruct.inputProcRefCon = (__bridge void*)self;

    // set playbackCallback as callback on our renderer for the output bus
    status = AudioUnitSetProperty(self.audioUnit, 
                              kAudioUnitProperty_SetRenderCallback, 
                              kAudioUnitScope_Global, 
                              outputElement,
                              &callbackStruct,
                              sizeof(callbackStruct));
    [self hasError:status:__FILE__:__LINE__];



    callbackStruct.inputProc = fxAudioUnitRenderCallback;
    callbackStruct.inputProcRefCon = (__bridge void*)self;

    // set input callback to input AU
    status = AudioUnitSetProperty(self.fxAudioUnit, 
                              kAudioUnitProperty_SetRenderCallback, 
                              kAudioUnitScope_Global, 
                              0, 
                              &callbackStruct, 
                              sizeof(callbackStruct));

    [self hasError:status:__FILE__:__LINE__];

    // reset flag to 0
    flag = 0;

    /*
     we need to tell the audio unit to allocate the render buffer,
     that we can directly write into it.
     */
    status = AudioUnitSetProperty(self.audioUnit, 
                                  kAudioUnitProperty_ShouldAllocateBuffer,
                              kAudioUnitScope_Output, 
                              inputElement,
                              &flag, 
                              sizeof(flag));

    status = AudioUnitSetProperty(self.fxAudioUnit, 
                              kAudioUnitProperty_ShouldAllocateBuffer,
                              kAudioUnitScope_Output, 
                              0,
                              &flag, 
                              sizeof(flag));

    /*
     we set the number of channels to mono and allocate our block size to
     1024 bytes.
     */
    _audioBuffer.mNumberChannels = 1;
    _audioBuffer.mDataByteSize = 512 * 2;
    _audioBuffer.mData = malloc( 512 * 2 );

    // Initialize the Audio Unit and cross fingers =)
    status = AudioUnitInitialize(self.fxAudioUnit);
    [self hasError:status:__FILE__:__LINE__];

    status = AudioUnitInitialize(self.audioUnit);
    [self hasError:status:__FILE__:__LINE__];

    NSLog(@"Started");

}

//For now, this just copies the buffer to self.audioBuffer
-(void)processBuffer: (AudioBufferList*) audioBufferList
{
    AudioBuffer sourceBuffer = audioBufferList->mBuffers[0];

    // we check here if the input data byte size has changed
    if (_audioBuffer.mDataByteSize != sourceBuffer.mDataByteSize) {
        // clear old buffer
        free(self.audioBuffer.mData);

        // assing new byte size and allocate them on mData
        _audioBuffer.mDataByteSize = sourceBuffer.mDataByteSize;
        _audioBuffer.mData = malloc(sourceBuffer.mDataByteSize);
}

// copy incoming audio data to the audio buffer
memcpy(self.audioBuffer.mData, audioBufferList->mBuffers[0].mData, audioBufferList->mBuffers[0].mDataByteSize);
}

#pragma mark - Error handling

-(void)hasError:(int)statusCode:(char*)file:(int)line 
{
    if (statusCode) {
        printf("Error Code responded %d in file %s on line %d\n", statusCode, file, line);
        exit(-1);
    }
}

@end

任何帮助将不胜感激。

Answer 1

这类问题出现的比较频繁，所以我曾经写过一篇mini-tutorial on this subject .但是，本指南确实是解决问题的具体方法，我现在觉得更优雅的方法是使用 Novocaine framework ，这消除了 iOS 上 AudioUnit 设置的许多麻烦。