How to correctly read decoded PCM samples on iOS using AVAssetReader — currently incorrect decoding

Question

I am currently working on an application as part of my Bachelor in Computer Science. The application will correlate data from the iPhone hardware (accelerometer, gps) and mu

Answer 1

I guess it is kind of late, but you could try this library:

https://bitbucket.org/artgillespie/tslibraryimport

After using this to save the audio into a file, you could process the data with render callbacks from MixerHost.

Answer 2

If I were you I would either use kAudioUnitSubType_AudioFilePlayer to play the file and access its samples with the units render callback.

Or

Use ExtAudioFileRef to extract the samples straight to a buffer.

Answer 3

Currently, I am also working on a project which involves extracting audio samples from iTunes Library into AudioUnit.

The audiounit render call back is included for your reference. The input format is set as SInt16StereoStreamFormat.

I have made use of Michael Tyson's circular buffer implementation - TPCircularBuffer as the buffer storage. Very easy to use and understand!!! Thanks Michael!

- (void) loadBuffer:(NSURL *)assetURL_
{
    if (nil != self.iPodAssetReader) {
        [iTunesOperationQueue cancelAllOperations];

        [self cleanUpBuffer];
    }

    NSDictionary *outputSettings = [NSDictionary dictionaryWithObjectsAndKeys:
                                    [NSNumber numberWithInt:kAudioFormatLinearPCM], AVFormatIDKey, 
                                    [NSNumber numberWithFloat:44100.0], AVSampleRateKey,
                                    [NSNumber numberWithInt:16], AVLinearPCMBitDepthKey,
                                    [NSNumber numberWithBool:NO], AVLinearPCMIsNonInterleaved,
                                    [NSNumber numberWithBool:NO], AVLinearPCMIsFloatKey,
                                    [NSNumber numberWithBool:NO], AVLinearPCMIsBigEndianKey,
                                    nil];

    AVURLAsset *asset = [AVURLAsset URLAssetWithURL:assetURL_ options:nil];
    if (asset == nil) {
        NSLog(@"asset is not defined!");
        return;
    }

    NSLog(@"Total Asset Duration: %f", CMTimeGetSeconds(asset.duration));

    NSError *assetError = nil;
    self.iPodAssetReader = [AVAssetReader assetReaderWithAsset:asset error:&assetError];
    if (assetError) {
        NSLog (@"error: %@", assetError);
        return;
    }

    AVAssetReaderOutput *readerOutput = [AVAssetReaderAudioMixOutput assetReaderAudioMixOutputWithAudioTracks:asset.tracks audioSettings:outputSettings];

    if (! [iPodAssetReader canAddOutput: readerOutput]) {
        NSLog (@"can't add reader output... die!");
        return;
    }

    // add output reader to reader
    [iPodAssetReader addOutput: readerOutput];

    if (! [iPodAssetReader startReading]) {
        NSLog(@"Unable to start reading!");
        return;
    }

    // Init circular buffer
    TPCircularBufferInit(&playbackState.circularBuffer, kTotalBufferSize);

    __block NSBlockOperation * feediPodBufferOperation = [NSBlockOperation blockOperationWithBlock:^{
        while (![feediPodBufferOperation isCancelled] && iPodAssetReader.status != AVAssetReaderStatusCompleted) {
            if (iPodAssetReader.status == AVAssetReaderStatusReading) {
                // Check if the available buffer space is enough to hold at least one cycle of the sample data
                if (kTotalBufferSize - playbackState.circularBuffer.fillCount >= 32768) {
                    CMSampleBufferRef nextBuffer = [readerOutput copyNextSampleBuffer];

                    if (nextBuffer) {
                        AudioBufferList abl;
                        CMBlockBufferRef blockBuffer;
                        CMSampleBufferGetAudioBufferListWithRetainedBlockBuffer(nextBuffer, NULL, &abl, sizeof(abl), NULL, NULL, kCMSampleBufferFlag_AudioBufferList_Assure16ByteAlignment, &blockBuffer);
                        UInt64 size = CMSampleBufferGetTotalSampleSize(nextBuffer);

                        int bytesCopied = TPCircularBufferProduceBytes(&playbackState.circularBuffer, abl.mBuffers[0].mData, size);

                        if (!playbackState.bufferIsReady && bytesCopied > 0) {
                            playbackState.bufferIsReady = YES;
                        }

                        CFRelease(nextBuffer);
                        CFRelease(blockBuffer);
                    }
                    else {
                        break;
                    }
                }
            }
        }
        NSLog(@"iPod Buffer Reading Finished");
    }];

    [iTunesOperationQueue addOperation:feediPodBufferOperation];
}

static OSStatus ipodRenderCallback (

                                     void                        *inRefCon,      // A pointer to a struct containing the complete audio data 
                                     //    to play, as well as state information such as the  
                                     //    first sample to play on this invocation of the callback.
                                     AudioUnitRenderActionFlags  *ioActionFlags, // Unused here. When generating audio, use ioActionFlags to indicate silence 
                                     //    between sounds; for silence, also memset the ioData buffers to 0.
                                     const AudioTimeStamp        *inTimeStamp,   // Unused here.
                                     UInt32                      inBusNumber,    // The mixer unit input bus that is requesting some new
                                     //        frames of audio data to play.
                                     UInt32                      inNumberFrames, // The number of frames of audio to provide to the buffer(s)
                                     //        pointed to by the ioData parameter.
                                     AudioBufferList             *ioData         // On output, the audio data to play. The callback's primary 
                                     //        responsibility is to fill the buffer(s) in the 
                                     //        AudioBufferList.
                                     ) 
{
    Audio* audioObject   = (Audio*)inRefCon;

    AudioSampleType *outSample          = (AudioSampleType *)ioData->mBuffers[0].mData;

    // Zero-out all the output samples first
    memset(outSample, 0, inNumberFrames * kUnitSize * 2);

    if ( audioObject.playingiPod && audioObject.bufferIsReady) {
        // Pull audio from circular buffer
        int32_t availableBytes;

        AudioSampleType *bufferTail     = TPCircularBufferTail(&audioObject.circularBuffer, &availableBytes);

        memcpy(outSample, bufferTail, MIN(availableBytes, inNumberFrames * kUnitSize * 2) );
        TPCircularBufferConsume(&audioObject.circularBuffer, MIN(availableBytes, inNumberFrames * kUnitSize * 2) );
        audioObject.currentSampleNum += MIN(availableBytes / (kUnitSize * 2), inNumberFrames);

        if (availableBytes <= inNumberFrames * kUnitSize * 2) {
            // Buffer is running out or playback is finished
            audioObject.bufferIsReady = NO;
            audioObject.playingiPod = NO;
            audioObject.currentSampleNum = 0;

            if ([[audioObject delegate] respondsToSelector:@selector(playbackDidFinish)]) {
                [[audioObject delegate] performSelector:@selector(playbackDidFinish)];
            }
        }
    }

    return noErr;
}

- (void) setupSInt16StereoStreamFormat {

    // The AudioUnitSampleType data type is the recommended type for sample data in audio
    //    units. This obtains the byte size of the type for use in filling in the ASBD.
    size_t bytesPerSample = sizeof (AudioSampleType);

    // Fill the application audio format struct's fields to define a linear PCM, 
    //        stereo, noninterleaved stream at the hardware sample rate.
    SInt16StereoStreamFormat.mFormatID          = kAudioFormatLinearPCM;
    SInt16StereoStreamFormat.mFormatFlags       = kAudioFormatFlagsCanonical;
    SInt16StereoStreamFormat.mBytesPerPacket    = 2 * bytesPerSample;   // *** kAudioFormatFlagsCanonical <- implicit interleaved data => (left sample + right sample) per Packet 
    SInt16StereoStreamFormat.mFramesPerPacket   = 1;
    SInt16StereoStreamFormat.mBytesPerFrame     = SInt16StereoStreamFormat.mBytesPerPacket * SInt16StereoStreamFormat.mFramesPerPacket;
    SInt16StereoStreamFormat.mChannelsPerFrame  = 2;                    // 2 indicates stereo
    SInt16StereoStreamFormat.mBitsPerChannel    = 8 * bytesPerSample;
    SInt16StereoStreamFormat.mSampleRate        = graphSampleRate;


    NSLog (@"The stereo stream format for the \"iPod\" mixer input bus:");
    [self printASBD: SInt16StereoStreamFormat];
}