之前幾篇文章記錄了視頻的軟、硬編碼過程，接下來將記錄下音頻的軟、硬編碼過程，學習、工作之余，以免忘記。
視頻編碼地址：
iOS音視頻開發(fā)-視頻會話捕捉
iOS音視頻開發(fā)-視頻硬編碼(H264)
iOS音視頻開發(fā)-視頻軟編碼(x264編碼H.264文件)
iOS音視頻開發(fā)-視頻軟編碼(FFmpeg+x264編碼H.264文件)
PCM數(shù)據(jù)
PCM(Pulse Code Modulation)也被稱為脈沖編碼調制。PCM音頻數(shù)據(jù)是未經壓縮的音頻采樣數(shù)據(jù)裸流，它是由模擬信號經過采樣、量化、編碼轉換成的標準的數(shù)字音頻數(shù)據(jù)。
移動端對音頻的實時采集編碼傳輸，一般為將采集的音頻數(shù)據(jù)設置為PCM格式數(shù)據(jù)，然后將PCM編碼為AAC格式數(shù)據(jù)，以便后續(xù)傳輸。
PCM的數(shù)據(jù)格式，這里有篇文章介紹的很好，后續(xù)代碼中的采樣率、聲道等均參考此文章設置。
PCM數(shù)據(jù)格式文章地址：點這里
ADTS
ADTS全稱是(Audio Data Transport Stream)，是AAC的一種十分常見的傳輸格式。
將PCM數(shù)據(jù)編碼為AAC的時候需要將每幀的AAC數(shù)據(jù)添加ADTS header，否則將無法解碼播放。
ADTS數(shù)據(jù)格式分為兩部分：
固定頭部：adts_fixed_header
可變頭部：adts_variable_header
詳見Wiki，地址在文章末尾。
主要代碼
1、音頻捕獲代碼
#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 -- 對象銷毀方法
- (void)dealloc{
AudioComponentInstanceDispose(_outInstance);
}
#pragma mark -- 對外API（控制是否捕捉音頻數(shù)據(jù)）
- (void)startRunning{
AudioOutputUnitStart(_outInstance);
}
-(void)stopRunning{
AudioOutputUnitStop(_outInstance);
}
#pragma mark -- 對外API（設置捕獲音頻數(shù)據(jù)配置項）
- (void)setConfig:(BBAudioConfig *)config{
_config = config;
[self private_setupAudioSession];
}
#pragma mark -- 私有API（初始化音頻會話）
- (void)private_setupAudioSession{
//0.初始化編碼器
self.encoder = [[BBAudioHardEncoder alloc] init];
self.encoder.config = self.config;
//1.獲取音頻會話實例
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.激活會話
[self.session setActive:YES error:&error];
if (error) {
NSLog(@"AVAudioSession setActiveError");
error = nil;
return;
}
//3.設置模式
[self.session setMode:AVAudioSessionModeVideoRecording error:&error];
if (error) {
NSLog(@"AVAudioSession setModeError");
error = nil;
return;
}
//4.設置音頻單元
AudioComponentDescription acd = {
.componentType = kAudioUnitType_Output,
.componentSubType = kAudioUnitSubType_RemoteIO,
.componentManufacturer = kAudioUnitManufacturer_Apple,
.componentFlags = 0,
.componentFlagsMask = 0,
};
//5.查找音頻單元
self.component = AudioComponentFindNext(NULL, &acd);
//6.獲取音頻單元實例
OSStatus status = AudioComponentInstanceNew(self.component, &_outInstance);
if (status != noErr) {
NSLog(@"AudioSource new AudioComponent error");
status = noErr;
return;
}
//7.設置音頻單元屬性-->可讀寫 0-->不可讀寫 1-->可讀寫
UInt32 flagOne = 1;
AudioUnitSetProperty(_outInstance, kAudioOutputUnitProperty_EnableIO, kAudioUnitScope_Input, 1, &flagOne, sizeof(flagOne));
//8.設置音頻單元屬性-->音頻流
AudioStreamBasicDescription asbd = {0};
asbd.mSampleRate = self.config.sampleRate;//采樣率
asbd.mFormatID = kAudioFormatLinearPCM;//原始數(shù)據(jù)為PCM格式
asbd.mFormatFlags = kAudioFormatFlagIsSignedInteger | kAudioFormatFlagsNativeEndian | kAudioFormatFlagIsPacked;
asbd.mChannelsPerFrame = (UInt32)self.config.channels;//每幀的聲道數(shù)量
asbd.mFramesPerPacket = 1;//每個數(shù)據(jù)包多少幀
asbd.mBitsPerChannel = 16;//16位
asbd.mBytesPerFrame = asbd.mChannelsPerFrame * asbd.mBitsPerChannel / 8;//每幀多少字節(jié) bytes -> bit / 8
asbd.mBytesPerPacket = asbd.mFramesPerPacket * asbd.mBytesPerFrame;//每個包多少字節(jié)
status = AudioUnitSetProperty(_outInstance, kAudioUnitProperty_StreamFormat, kAudioUnitScope_Output, 1, &asbd, sizeof(asbd));
if (status != noErr) {
NSLog(@"AudioUnitSetProperty StreamFormat error");
status = noErr;
return;
}
//9.設置回調函數(shù)
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.初始化音頻單元
status = AudioUnitInitialize(_outInstance);
if (status != noErr) {
NSLog(@"AudioUnitInitialize error");
status = noErr;
return;
}
//11.設置優(yōu)先采樣率
[self.session setPreferredSampleRate:self.config.sampleRate error:&error];
if (error) {
NSLog(@"AudioSource setPreferredSampleRate error");
error = nil;
return;
}
//12.aac文件夾地址
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 -- 音頻流回調函數(shù)
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、編碼代碼
#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.輸入流
AudioStreamBasicDescription inputFormat = {0};
inputFormat.mSampleRate = self.config.sampleRate;//采樣率
inputFormat.mFormatID = kAudioFormatLinearPCM;//PCM采樣
inputFormat.mFormatFlags = kAudioFormatFlagIsSignedInteger | kAudioFormatFlagsNativeEndian | kAudioFormatFlagIsPacked;
inputFormat.mChannelsPerFrame = (UInt32)self.config.channels;//每幀聲道數(shù)
inputFormat.mFramesPerPacket = 1;//每包幀數(shù)
inputFormat.mBitsPerChannel = 16;//每聲道位數(shù)
inputFormat.mBytesPerFrame = inputFormat.mBitsPerChannel / 8 * inputFormat.mChannelsPerFrame;//每幀的字節(jié)數(shù)
inputFormat.mBytesPerPacket = inputFormat.mBytesPerFrame * inputFormat.mFramesPerPacket;//每包字節(jié)數(shù)
//2.輸出流
AudioStreamBasicDescription outputFormat;
//2.1初始清零
memset(&outputFormat, 0, sizeof(outputFormat));
//2.2音頻流，在正常播放情況下的幀率。如果是壓縮的格式，這個屬性表示解壓縮后的幀率。幀率不能為0。
outputFormat.mSampleRate = inputFormat.mSampleRate;
//2.3AAC編碼 kAudioFormatMPEG4AAC kAudioFormatMPEG4AAC_HE_V2
outputFormat.mFormatID = kAudioFormatMPEG4AAC;
//2.4無損編碼，0則無
outputFormat.mFormatFlags = kMPEG4Object_AAC_LC;
//2.5每一個packet的音頻數(shù)據(jù)大小。如果的動態(tài)大小設置為0。動態(tài)大小的格式需要用AudioStreamPacketDescription來確定每個packet的大小。
outputFormat.mBytesPerPacket = 0;
//2.6每幀的聲道數(shù)
outputFormat.mChannelsPerFrame = (UInt32)self.config.channels;
//2.7每個packet的幀數(shù)。如果是未壓縮的音頻數(shù)據(jù)，值是1。動態(tài)幀率格式，這個值是一個較大的固定數(shù)字，比如說AAC的1024。如果是動態(tài)大小幀數(shù)（比如Ogg格式）設置為0。
outputFormat.mFramesPerPacket = 1024;
//2.8每幀的bytes數(shù)，每幀的大小。每一幀的起始點到下一幀的起始點。如果是壓縮格式，設置為0 。
outputFormat.mBytesPerFrame = 0;
//2.9語音每采樣點占用位數(shù) 壓縮格式設置為0
outputFormat.mBitsPerChannel = 0;
//2.10字節(jié)對齊，填0.
outputFormat.mReserved = 0;
//3.編碼器參數(shù)
const OSType subtype = kAudioFormatMPEG4AAC;
AudioClassDescription requestedCodecs[2] = {
{
kAudioEncoderComponentType,
subtype,
kAppleSoftwareAudioCodecManufacturer
},
{
kAudioEncoderComponentType,
subtype,
kAppleHardwareAudioCodecManufacturer
}
};
//4.編碼器
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.初始化一個輸出緩沖列表
AudioBufferList outBufferList;
outBufferList.mNumberBuffers = 1;
outBufferList.mBuffers[0].mNumberChannels = bufferList.mBuffers[0].mNumberChannels;
outBufferList.mBuffers[0].mDataByteSize = bufferList.mBuffers[0].mDataByteSize; // 設置緩沖區(qū)大小
outBufferList.mBuffers[0].mData = aacBuf; // 設置AAC緩沖區(qū)
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(@"音頻編碼失敗");
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到緩沖區(qū)
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
以上代碼為主要代碼，配置代碼無非就是采樣率：44.1kHz，聲道：雙聲道。
完整代碼地址：https://github.com/ibabyblue/PCMHardEncodeToAAC
將編碼的AAC數(shù)據(jù)寫入本地文件，利用VLC播放器可以直接播放.aac格式文件，測試很方便。
寫在最后，學習過程中非常感謝Jovins、iossigner分享的干活，感恩！
參考地址：
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
