我已经成功地使用AVAssetReader从一个MPMediaItem中获取了原始数据，在组合了几个SO问题的答案后，比如这个和这个，以及一篇漂亮的博客文章。我也可以使用FMOD播放这些原始数据，但随后出现了问题。
结果音频的质量似乎低于原始音轨。虽然AVAssetTrack formatDescription告诉我数据中有2个通道，但结果听起来是单声道的。它听起来也有点潮湿（不那么脆），就像比特率降低了一样。
我是做错了什么，还是AVAssetReader故意降低了MPMediaItem数据的质量（因为盗版）？
#define OUTPUTRATE 44100
初始化AVAssetReader和AVAssetReaderTrackOutput
// prepare AVAsset and AVAssetReaderOutput etc
MPMediaItem* mediaItem = ...;
NSURL* ipodAudioUrl = [mediaItem valueForProperty:MPMediaItemPropertyAssetURL];
AVURLAsset * asset = [[AVURLAsset alloc] initWithURL:ipodAudioUrl options:nil];
NSError * error = nil;
assetReader = [[AVAssetReader alloc] initWithAsset:asset error:&error];
if(error)
NSLog(@"error creating reader: %@", [error debugDescription]);
AVAssetTrack* songTrack = [asset.tracks objectAtIndex:0];
NSArray* trackDescriptions = songTrack.formatDescriptions;
numChannels = 2;
for(unsigned int i = 0; i < [trackDescriptions count]; ++i)
{
CMAudioFormatDescriptionRef item = (CMAudioFormatDescriptionRef)[trackDescriptions objectAtIndex:i];
const AudioStreamBasicDescription* bobTheDesc = CMAudioFormatDescriptionGetStreamBasicDescription (item);
if(bobTheDesc && bobTheDesc->mChannelsPerFrame == 1) {
numChannels = 1;
}
}
NSDictionary* outputSettingsDict = [[[NSDictionary alloc] initWithObjectsAndKeys:
[NSNumber numberWithInt:kAudioFormatLinearPCM],AVFormatIDKey,
[NSNumber numberWithInt:OUTPUTRATE],AVSampleRateKey,
[NSNumber numberWithInt:16],AVLinearPCMBitDepthKey,
[NSNumber numberWithBool:NO],AVLinearPCMIsBigEndianKey,
[NSNumber numberWithBool:NO],AVLinearPCMIsFloatKey,
[NSNumber numberWithBool:NO],AVLinearPCMIsNonInterleaved,
nil] autorelease];
AVAssetReaderTrackOutput * output = [[[AVAssetReaderTrackOutput alloc] initWithTrack:songTrack outputSettings:outputSettingsDict] autorelease];
[assetReader addOutput:output];
[assetReader startReading];
初始化FMOD和FMOD声音
// Init FMOD
FMOD_RESULT result = FMOD_OK;
unsigned int version = 0;
/*
Create a System object and initialize
*/
result = FMOD::System_Create(&system);
ERRCHECK(result);
result = system->getVersion(&version);
ERRCHECK(result);
if (version < FMOD_VERSION)
{
fprintf(stderr, "You are using an old version of FMOD %08x. This program requires %08xn", version, FMOD_VERSION);
exit(-1);
}
result = system->setSoftwareFormat(OUTPUTRATE, FMOD_SOUND_FORMAT_PCM16, 1, 0, FMOD_DSP_RESAMPLER_LINEAR);
ERRCHECK(result);
result = system->init(32, FMOD_INIT_NORMAL | FMOD_INIT_ENABLE_PROFILE, NULL);
ERRCHECK(result);
// Init FMOD sound stream
CMTimeRange timeRange = [songTrack timeRange];
float durationInSeconds = timeRange.duration.value / timeRange.duration.timescale;
FMOD_CREATESOUNDEXINFO exinfo = {0};
memset(&exinfo, 0, sizeof(FMOD_CREATESOUNDEXINFO));
exinfo.cbsize = sizeof(FMOD_CREATESOUNDEXINFO); /* required. */
exinfo.decodebuffersize = OUTPUTRATE; /* Chunk size of stream update in samples. This will be the amount of data passed to the user callback. */
exinfo.length = OUTPUTRATE * numChannels * sizeof(signed short) * durationInSeconds; /* Length of PCM data in bytes of whole song (for Sound::getLength) */
exinfo.numchannels = numChannels; /* Number of channels in the sound. */
exinfo.defaultfrequency = OUTPUTRATE; /* Default playback rate of sound. */
exinfo.format = FMOD_SOUND_FORMAT_PCM16; /* Data format of sound. */
exinfo.pcmreadcallback = pcmreadcallback; /* User callback for reading. */
exinfo.pcmsetposcallback = pcmsetposcallback; /* User callback for seeking. */
result = system->createStream(NULL, FMOD_OPENUSER, &exinfo, &sound);
ERRCHECK(result);
result = system->playSound(FMOD_CHANNEL_FREE, sound, false, &channel);
ERRCHECK(result);
从AVAssetReaderTrackOutput读取到环形缓冲区
AVAssetReaderTrackOutput * trackOutput = (AVAssetReaderTrackOutput *)[assetReader.outputs objectAtIndex:0];
CMSampleBufferRef sampleBufferRef = [trackOutput copyNextSampleBuffer];
if (sampleBufferRef)
{
AudioBufferList audioBufferList;
CMBlockBufferRef blockBuffer;
CMSampleBufferGetAudioBufferListWithRetainedBlockBuffer(sampleBufferRef, NULL, &audioBufferList, sizeof(audioBufferList), NULL, NULL, 0, &blockBuffer);
if(blockBuffer == NULL)
{
stopLoading = YES;
continue;
}
if(&audioBufferList == NULL)
{
stopLoading = YES;
continue;
}
if(audioBufferList.mNumberBuffers != 1)
NSLog(@"numBuffers = %lu", audioBufferList.mNumberBuffers);
for( int y=0; y<audioBufferList.mNumberBuffers; y++ )
{
AudioBuffer audioBuffer = audioBufferList.mBuffers[y];
SInt8 *frame = (SInt8*)audioBuffer.mData;
for(int i=0; i<audioBufferList.mBuffers[y].mDataByteSize; i++)
{
ringBuffer->push_back(frame[i]);
}
}
CMSampleBufferInvalidate(sampleBufferRef);
CFRelease(sampleBufferRef);
}
我不熟悉FMOD，所以我不能在那里发表评论。AVAssetReader不做任何"复制保护"的事情，所以这并不令人担忧。（如果您可以获得AVAssetURL，则该曲目是无DRM的）
由于您使用的是非交错缓冲区，因此只有一个缓冲区，所以我猜您的最后一位代码可能是错误的
这里有一个对我来说运行良好的代码示例。顺便说一句，你的for循环可能不会很有性能。您可以考虑使用memcpy或其他。。。如果您不受现有环形缓冲区的限制，请尝试TPCircularBuffer(https://github.com/michaeltyson/TPCircularBuffer)太神奇了。
CMSampleBufferRef nextBuffer = NULL;
if(_reader.status == AVAssetReaderStatusReading)
{
nextBuffer = [_readerOutput copyNextSampleBuffer];
}
if (nextBuffer)
{
AudioBufferList abl;
CMBlockBufferRef blockBuffer;
CMSampleBufferGetAudioBufferListWithRetainedBlockBuffer(
nextBuffer,
NULL,
&abl,
sizeof(abl),
NULL,
NULL,
kCMSampleBufferFlag_AudioBufferList_Assure16ByteAlignment,
&blockBuffer);
// the correct way to get the number of bytes in the buffer
size_t size = CMSampleBufferGetTotalSampleSize(nextBuffer);
memcpy(ringBufferTail, abl.mBuffers[0].mData, size);
CFRelease(nextBuffer);
CFRelease(blockBuffer);
}
希望这能帮助
您正在初始化FMOD以输出单声道音频。尝试
result = system->setSoftwareFormat(OUTPUTRATE, FMOD_SOUND_FORMAT_PCM16, 2, 0, FMOD_DSP_RESAMPLER_LINEAR);