How to decode AAC audio buffer to PCM buffer in iOS? [closed]

Question

I am trying to decode AAC audio to PCM audio in iOS, what the best way to do this?Any sample code would be very helpful...Is there any simple APIs to do this..?

Answer 1

I have sample code to do it.

At start you should configure in/out ASBD (AudioStreamBasicDescription) and create converter:

- (void)setupAudioConverter{
    AudioStreamBasicDescription outFormat;
    memset(&outFormat, 0, sizeof(outFormat));
    outFormat.mSampleRate       = 44100;
    outFormat.mFormatID         = kAudioFormatLinearPCM;
    outFormat.mFormatFlags      = kLinearPCMFormatFlagIsSignedInteger;
    outFormat.mBytesPerPacket   = 2;
    outFormat.mFramesPerPacket  = 1;
    outFormat.mBytesPerFrame    = 2;
    outFormat.mChannelsPerFrame = 1;
    outFormat.mBitsPerChannel   = 16;
    outFormat.mReserved         = 0;


    AudioStreamBasicDescription inFormat;
    memset(&inFormat, 0, sizeof(inFormat));
    inFormat.mSampleRate        = 44100;
    inFormat.mFormatID          = kAudioFormatMPEG4AAC;
    inFormat.mFormatFlags       = kMPEG4Object_AAC_LC;
    inFormat.mBytesPerPacket    = 0;
    inFormat.mFramesPerPacket   = 1024;
    inFormat.mBytesPerFrame     = 0;
    inFormat.mChannelsPerFrame  = 1;
    inFormat.mBitsPerChannel    = 0;
    inFormat.mReserved          = 0;

    OSStatus status =  AudioConverterNew(&inFormat, &outFormat, &_audioConverter);
    if (status != 0) {
        printf("setup converter error, status: %i\n", (int)status);
    }
}

After that you should make callback function for audio converter:

struct PassthroughUserData {
    UInt32 mChannels;
    UInt32 mDataSize;
    const void* mData;
    AudioStreamPacketDescription mPacket;
};


OSStatus inInputDataProc(AudioConverterRef aAudioConverter,
                         UInt32* aNumDataPackets /* in/out */,
                         AudioBufferList* aData /* in/out */,
                         AudioStreamPacketDescription** aPacketDesc,
                         void* aUserData)
{

    PassthroughUserData* userData = (PassthroughUserData*)aUserData;
    if (!userData->mDataSize) {
        *aNumDataPackets = 0;
        return kNoMoreDataErr;
    }

    if (aPacketDesc) {
        userData->mPacket.mStartOffset = 0;
        userData->mPacket.mVariableFramesInPacket = 0;
        userData->mPacket.mDataByteSize = userData->mDataSize;
        *aPacketDesc = &userData->mPacket;
    }

    aData->mBuffers[0].mNumberChannels = userData->mChannels;
    aData->mBuffers[0].mDataByteSize = userData->mDataSize;
    aData->mBuffers[0].mData = const_cast<void*>(userData->mData);

    // No more data to provide following this run.
    userData->mDataSize = 0;

    return noErr;
}

And method for frame decoding:

- (void)decodeAudioFrame:(NSData *)frame withPts:(NSInteger)pts{
    if(!_audioConverter){
        [self setupAudioConverter];
    }

    PassthroughUserData userData = { 1, (UInt32)frame.length, [frame bytes]};
    NSMutableData *decodedData = [NSMutableData new];

    const uint32_t MAX_AUDIO_FRAMES = 128;
    const uint32_t maxDecodedSamples = MAX_AUDIO_FRAMES * 1;

    do{
        uint8_t *buffer = (uint8_t *)malloc(maxDecodedSamples * sizeof(short int));
        AudioBufferList decBuffer;
        decBuffer.mNumberBuffers = 1;
        decBuffer.mBuffers[0].mNumberChannels = 1;
        decBuffer.mBuffers[0].mDataByteSize = maxDecodedSamples * sizeof(short int);
        decBuffer.mBuffers[0].mData = buffer;

        UInt32 numFrames = MAX_AUDIO_FRAMES;

        AudioStreamPacketDescription outPacketDescription;
        memset(&outPacketDescription, 0, sizeof(AudioStreamPacketDescription));
        outPacketDescription.mDataByteSize = MAX_AUDIO_FRAMES;
        outPacketDescription.mStartOffset = 0;
        outPacketDescription.mVariableFramesInPacket = 0;

        OSStatus rv = AudioConverterFillComplexBuffer(_audioConverter,
                                                      inInputDataProc,
                                                      &userData,
                                                      &numFrames /* in/out */,
                                                      &decBuffer,
                                                      &outPacketDescription);

        if (rv && rv != kNoMoreDataErr) {
            NSLog(@"Error decoding audio stream: %d\n", rv);
            break;
        }

        if (numFrames) {
            [decodedData appendBytes:decBuffer.mBuffers[0].mData length:decBuffer.mBuffers[0].mDataByteSize];
        }

        if (rv == kNoMoreDataErr) {
            break;
        }

    }while (true);

    //void *pData = (void *)[decodedData bytes];
    //audioRenderer->Render(&pData, decodedData.length, pts);
}

Answer 2

You need to use Core Audio. Look for Core Audio Overview in the Apple documentation.