之前几篇文章记录了视频的软、硬编码过程，接下来将记录下音频的软、硬编码过程，学习、工作之余，以免忘记。
视频编码地址：
iOS音视频开发-视频会话捕捉
iOS音视频开发-视频硬编码(H264)
iOS音视频开发-视频软编码(x264编码H.264文件)
iOS音视频开发-视频软编码(FFmpeg+x264编码H.264文件)
PCM数据
PCM(Pulse Code Modulation)也被称为脉冲编码调制。PCM音频数据是未经压缩的音频采样数据裸流，它是由模拟信号经过采样、量化、编码转换成的标准的数字音频数据。
移动端对音频的实时采集编码传输，一般为将采集的音频数据设置为PCM格式数据，然后将PCM编码为AAC格式数据，以便后续传输。
PCM的数据格式，这里有篇文章介绍的很好，后续代码中的采样率、声道等均参考此文章设置。
PCM数据格式文章地址：点这里
ADTS
ADTS全称是(Audio Data Transport Stream)，是AAC的一种十分常见的传输格式。
将PCM数据编码为AAC的时候需要将每帧的AAC数据添加ADTS header，否则将无法解码播放。
ADTS数据格式分为两部分：
固定头部：adts_fixed_header
可变头部：adts_variable_header
详见Wiki，地址在文章末尾。
主要代码
1、音频捕获代码
#import "BBAudioCapture.h"
#import <AVFoundation/AVFoundation.h>
#import "BBAudioConfig.h"
#import "BBAudioHardEncoder.h"
#import "BBAudioHardEncoder.h"
@interface BBAudioCapture ()
{
AudioComponentInstance _outInstance;
}
@property (nonatomic, assign) AudioComponent component;
@property (nonatomic, strong) AVAudioSession *session;
@property (nonatomic, strong) BBAudioHardEncoder *encoder;
@property (nonatomic, strong) NSFileHandle *handle;
@end
@implementation BBAudioCapture
#pragma mark -- 对象销毁方法
- (void)dealloc{
AudioComponentInstanceDispose(_outInstance);
}
#pragma mark -- 对外API（控制是否捕捉音频数据）
- (void)startRunning{
AudioOutputUnitStart(_outInstance);
}
-(void)stopRunning{
AudioOutputUnitStop(_outInstance);
}
#pragma mark -- 对外API（设置捕获音频数据配置项）
- (void)setConfig:(BBAudioConfig *)config{
_config = config;
[self private_setupAudioSession];
}
#pragma mark -- 私有API（初始化音频会话）
- (void)private_setupAudioSession{
//0.初始化编码器
self.encoder = [[BBAudioHardEncoder alloc] init];
self.encoder.config = self.config;
//1.获取音频会话实例
self.session = [AVAudioSession sharedInstance];
NSError *error = nil;
[self.session setCategory:AVAudioSessionCategoryPlayAndRecord withOptions:AVAudioSessionCategoryOptionMixWithOthers | AVAudioSessionCategoryOptionDefaultToSpeaker error:&error];
if (error) {
NSLog(@"AVAudioSession setupError");
error = nil;
return;
}
//2.激活会话
[self.session setActive:YES error:&error];
if (error) {
NSLog(@"AVAudioSession setActiveError");
error = nil;
return;
}
//3.设置模式
[self.session setMode:AVAudioSessionModeVideoRecording error:&error];
if (error) {
NSLog(@"AVAudioSession setModeError");
error = nil;
return;
}
//4.设置音频单元
AudioComponentDescription acd = {
.componentType = kAudioUnitType_Output,
.componentSubType = kAudioUnitSubType_RemoteIO,
.componentManufacturer = kAudioUnitManufacturer_Apple,
.componentFlags = 0,
.componentFlagsMask = 0,
};
//5.查找音频单元
self.component = AudioComponentFindNext(NULL, &acd);
//6.获取音频单元实例
OSStatus status = AudioComponentInstanceNew(self.component, &_outInstance);
if (status != noErr) {
NSLog(@"AudioSource new AudioComponent error");
status = noErr;
return;
}
//7.设置音频单元属性-->可读写 0-->不可读写 1-->可读写
UInt32 flagOne = 1;
AudioUnitSetProperty(_outInstance, kAudioOutputUnitProperty_EnableIO, kAudioUnitScope_Input, 1, &flagOne, sizeof(flagOne));
//8.设置音频单元属性-->音频流
AudioStreamBasicDescription asbd = {0};
asbd.mSampleRate = self.config.sampleRate;//采样率
asbd.mFormatID = kAudioFormatLinearPCM;//原始数据为PCM格式
asbd.mFormatFlags = kAudioFormatFlagIsSignedInteger | kAudioFormatFlagsNativeEndian | kAudioFormatFlagIsPacked;
asbd.mChannelsPerFrame = (UInt32)self.config.channels;//每帧的声道数量
asbd.mFramesPerPacket = 1;//每个数据包多少帧
asbd.mBitsPerChannel = 16;//16位
asbd.mBytesPerFrame = asbd.mChannelsPerFrame * asbd.mBitsPerChannel / 8;//每帧多少字节 bytes -> bit / 8
asbd.mBytesPerPacket = asbd.mFramesPerPacket * asbd.mBytesPerFrame;//每个包多少字节
status = AudioUnitSetProperty(_outInstance, kAudioUnitProperty_StreamFormat, kAudioUnitScope_Output, 1, &asbd, sizeof(asbd));
if (status != noErr) {
NSLog(@"AudioUnitSetProperty StreamFormat error");
status = noErr;
return;
}
//9.设置回调函数
AURenderCallbackStruct cb;
cb.inputProcRefCon = (__bridge void *)self;
cb.inputProc = audioBufferCallBack;
status = AudioUnitSetProperty(_outInstance, kAudioOutputUnitProperty_SetInputCallback, kAudioUnitScope_Global, 1, &cb, sizeof(cb));
if(status != noErr){
NSLog(@"AudioUnitSetProperty StreamFormat InputCallback error");
status = noErr;
return;
}
//10.初始化音频单元
status = AudioUnitInitialize(_outInstance);
if (status != noErr) {
NSLog(@"AudioUnitInitialize error");
status = noErr;
return;
}
//11.设置优先采样率
[self.session setPreferredSampleRate:self.config.sampleRate error:&error];
if (error) {
NSLog(@"AudioSource setPreferredSampleRate error");
error = nil;
return;
}
//12.aac文件夹地址
NSString *audioPath = [[NSSearchPathForDirectoriesInDomains(NSDocumentDirectory, NSUserDomainMask, YES) lastObject] stringByAppendingPathComponent:@"test.aac"];
[[NSFileManager defaultManager] removeItemAtPath:audioPath error:nil];
[[NSFileManager defaultManager] createFileAtPath:audioPath contents:nil attributes:nil];
self.handle = [NSFileHandle fileHandleForWritingAtPath:audioPath];
}
#pragma mark -- 音频流回调函数
static OSStatus audioBufferCallBack(void *inRefCon,
AudioUnitRenderActionFlags *ioActionFlags,
const AudioTimeStamp *inTimeStamp,
UInt32 inBusNumber,
UInt32 inNumberFrames,
AudioBufferList *ioData) {
@autoreleasepool {
BBAudioCapture *capture = (__bridge BBAudioCapture *)inRefCon;
if(!capture) return -1;
AudioBuffer buffer;
buffer.mData = NULL;
buffer.mDataByteSize = 0;
buffer.mNumberChannels = 1;
AudioBufferList buffers;
buffers.mNumberBuffers = 1;
buffers.mBuffers[0] = buffer;
OSStatus status = AudioUnitRender(capture->_outInstance,
ioActionFlags,
inTimeStamp,
inBusNumber,
inNumberFrames,
&buffers);
if(status == noErr) {
[capture.encoder encodeWithBufferList:buffers completianBlock:^(NSData *encodedData, NSError *error) {
if (error) {
NSLog(@"error:%@",error);
return;
}
NSLog(@"write to file!");
[capture.handle writeData:encodedData];
}];
}
return status;
}
}
@end
2、编码代码
#import "BBAudioHardEncoder.h"
#import "BBAudioConfig.h"
@interface BBAudioHardEncoder ()
@property (nonatomic, assign) AudioConverterRef converterRef;
@end
@implementation BBAudioHardEncoder
- (AudioConverterRef)converterRef{
if (_converterRef == nil) {
[self private_setupAudioConvert];
}
return _converterRef;
}
- (void)dealloc {
AudioConverterDispose(_converterRef);
}
- (void)private_setupAudioConvert{
//1.输入流
AudioStreamBasicDescription inputFormat = {0};
inputFormat.mSampleRate = self.config.sampleRate;//采样率
inputFormat.mFormatID = kAudioFormatLinearPCM;//PCM采样
inputFormat.mFormatFlags = kAudioFormatFlagIsSignedInteger | kAudioFormatFlagsNativeEndian | kAudioFormatFlagIsPacked;
inputFormat.mChannelsPerFrame = (UInt32)self.config.channels;//每帧声道数
inputFormat.mFramesPerPacket = 1;//每包帧数
inputFormat.mBitsPerChannel = 16;//每声道位数
inputFormat.mBytesPerFrame = inputFormat.mBitsPerChannel / 8 * inputFormat.mChannelsPerFrame;//每帧的字节数
inputFormat.mBytesPerPacket = inputFormat.mBytesPerFrame * inputFormat.mFramesPerPacket;//每包字节数
//2.输出流
AudioStreamBasicDescription outputFormat;
//2.1初始清零
memset(&outputFormat, 0, sizeof(outputFormat));
//2.2音频流，在正常播放情况下的帧率。如果是压缩的格式，这个属性表示解压缩后的帧率。帧率不能为0。
outputFormat.mSampleRate = inputFormat.mSampleRate;
//2.3AAC编码 kAudioFormatMPEG4AAC kAudioFormatMPEG4AAC_HE_V2
outputFormat.mFormatID = kAudioFormatMPEG4AAC;
//2.4无损编码，0则无
outputFormat.mFormatFlags = kMPEG4Object_AAC_LC;
//2.5每一个packet的音频数据大小。如果的动态大小设置为0。动态大小的格式需要用AudioStreamPacketDescription来确定每个packet的大小。
outputFormat.mBytesPerPacket = 0;
//2.6每帧的声道数
outputFormat.mChannelsPerFrame = (UInt32)self.config.channels;
//2.7每个packet的帧数。如果是未压缩的音频数据，值是1。动态帧率格式，这个值是一个较大的固定数字，比如说AAC的1024。如果是动态大小帧数（比如Ogg格式）设置为0。
outputFormat.mFramesPerPacket = 1024;
//2.8每帧的bytes数，每帧的大小。每一帧的起始点到下一帧的起始点。如果是压缩格式，设置为0 。
outputFormat.mBytesPerFrame = 0;
//2.9语音每采样点占用位数 压缩格式设置为0
outputFormat.mBitsPerChannel = 0;
//2.10字节对齐，填0.
outputFormat.mReserved = 0;
//3.编码器参数
const OSType subtype = kAudioFormatMPEG4AAC;
AudioClassDescription requestedCodecs[2] = {
{
kAudioEncoderComponentType,
subtype,
kAppleSoftwareAudioCodecManufacturer
},
{
kAudioEncoderComponentType,
subtype,
kAppleHardwareAudioCodecManufacturer
}
};
//4.编码器
OSStatus result = AudioConverterNewSpecific(&inputFormat, &outputFormat, 2, requestedCodecs, &_converterRef);
if (result == noErr) {
NSLog(@"creat convert success!");
}else{
NSLog(@"creat convert error!");
_converterRef = nil;
}
}
- (void)encodeWithBufferList:(AudioBufferList)bufferList completianBlock:(void (^)(NSData *encodedData, NSError *error))completionBlock{
if (!self.converterRef) {
return;
}
int size = bufferList.mBuffers[0].mDataByteSize;
if (size <= 0) {
return;
}
char *aacBuf = malloc(size);
//1.初始化一个输出缓冲列表
AudioBufferList outBufferList;
outBufferList.mNumberBuffers = 1;
outBufferList.mBuffers[0].mNumberChannels = bufferList.mBuffers[0].mNumberChannels;
outBufferList.mBuffers[0].mDataByteSize = bufferList.mBuffers[0].mDataByteSize; // 设置缓冲区大小
outBufferList.mBuffers[0].mData = aacBuf; // 设置AAC缓冲区
UInt32 outputDataPacketSize = 1;
NSData *data = nil;
NSError *error = nil;
OSStatus status = AudioConverterFillComplexBuffer(_converterRef, inputDataProc, &bufferList, &outputDataPacketSize, &outBufferList, NULL);
if (status == 0){
NSData *rawAAC = [NSData dataWithBytes:outBufferList.mBuffers[0].mData length:outBufferList.mBuffers[0].mDataByteSize];
NSData *adtsHeader = [self getADTSDataWithPacketLength:rawAAC.length];
NSMutableData *fullData = [NSMutableData dataWithData:adtsHeader];
[fullData appendData:rawAAC];
data = fullData;
}else{
error = [NSError errorWithDomain:NSOSStatusErrorDomain code:status userInfo:nil];
NSLog(@"音频编码失败");
return;
}
if (completionBlock) {
dispatch_async(dispatch_get_global_queue(0, 0), ^{
completionBlock(data, error);
});
}
free(aacBuf);
}
#pragma mark -- AudioCallBack
OSStatus inputDataProc(AudioConverterRef inConverter, UInt32 *ioNumberDataPackets, AudioBufferList *ioData,AudioStreamPacketDescription **outDataPacketDescription, void *inUserData) {
//填充PCM到缓冲区
AudioBufferList bufferList = *(AudioBufferList*)inUserData;
ioData->mBuffers[0].mNumberChannels = 1;
ioData->mBuffers[0].mData = bufferList.mBuffers[0].mData;
ioData->mBuffers[0].mDataByteSize = bufferList.mBuffers[0].mDataByteSize;
ioData->mNumberBuffers = 1;
return noErr;
}
/**
* Add ADTS header at the beginning of each and every AAC packet.
* This is needed as MediaCodec encoder generates a packet of raw
* AAC data.
*
* Note the packetLen must count in the ADTS header itself.
* See: http://wiki.multimedia.cx/index.php?title=ADTS
* Also: http://wiki.multimedia.cx/index.php?title=MPEG-4_Audio#Channel_Configurations
**/
- (NSData *)getADTSDataWithPacketLength:(NSInteger)packetLength {
int adtsLength = 7;
char *packet = malloc(sizeof(char) * adtsLength);
// Variables Recycled by addADTStoPacket
int profile = 2; //AAC LC
//39=MediaCodecInfo.CodecProfileLevel.AACObjectELD;
int freqIdx = 4; //44.1KHz
int chanCfg = 1; //MPEG-4 Audio Channel Configuration. 1 Channel front-center
NSUInteger fullLength = adtsLength + packetLength;
// fill in ADTS data
packet[0] = (char)0xFF; // 11111111 = syncword
packet[1] = (char)0xF9; // 1111 1 00 1 = syncword MPEG-2 Layer CRC
packet[2] = (char)(((profile-1)<<6) + (freqIdx<<2) +(chanCfg>>2));
packet[3] = (char)(((chanCfg&3)<<6) + (fullLength>>11));
packet[4] = (char)((fullLength&0x7FF) >> 3);
packet[5] = (char)(((fullLength&7)<<5) + 0x1F);
packet[6] = (char)0xFC;
NSData *data = [NSData dataWithBytesNoCopy:packet length:adtsLength freeWhenDone:YES];
return data;
}
@end
以上代码为主要代码，配置代码无非就是采样率：44.1kHz，声道：双声道。
完整代码地址：https://github.com/ibabyblue/PCMHardEncodeToAAC
将编码的AAC数据写入本地文件，利用VLC播放器可以直接播放.aac格式文件，测试很方便。
写在最后，学习过程中非常感谢Jovins、iossigner分享的干活，感恩！
参考地址：
http://blog.csdn.net/ownwell/article/details/8114121/
https://wiki.multimedia.cx/index.php?title=ADTS
https://developer.apple.com/documentation/audiotoolbox/audio_converter_services?language=objc
网友评论