关于AAC音频格式基本情况,可参考维基百科http://en.wikipedia.org/wiki/Advanced_Audio_Coding
AAC音频格式分析
AAC音频格式有ADIF和ADTS:
ADIF:Audio Data Interchange Format 音频数据交换格式。这种格式的特征是可以确定的找到这个音频数据的开始,不需进行在音频数据流中间开始的解码,即它的解码必须在明确定义的开始处进行。故这种格式常用在磁盘文件中。
ADTS:Audio Data Transport Stream 音频数据传输流。这种格式的特征是它是一个有同步字的比特流,解码可以在这个流中任何位置开始。它的特征类似于mp3数据流格式。
简单说,ADTS可以在任意帧解码,也就是说它每一帧都有头信息。ADIF只有一个统一的头,所以必须得到所有的数据后解码。且这两种的header的格式也是不同的,目前一般编码后的和抽取出的都是ADTS格式的音频流。
语音系统对实时性要求较高,基本是这样一个流程,采集音频数据,本地编码,数据上传,服务器处理,数据下发,本地解码
ADTS是帧序列,本身具备流特征,在音频流的传输与处理方面更加合适。
ADTS帧结构:
header | body |
ADTS帧首部结构:
序号 | 域 | 长度(bits) | 说明 |
1 | Syncword | 12 | all bits must be 1 |
2 | MPEG version | 1 | 0 for MPEG-4, 1 for MPEG-2 |
3 | Layer | 2 | always 0 |
4 | Protection Absent | 1 | et to 1 if there is no CRC and 0 if there is CRC |
5 | Profile | 2 | the MPEG-4 Audio Object Type minus 1 |
6 | MPEG-4 Sampling Frequency Index | 4 | MPEG-4 Sampling Frequency Index (15 is forbidden) |
7 | Private Stream | 1 | set to 0 when encoding, ignore when decoding |
8 | MPEG-4 Channel Configuration | 3 | MPEG-4 Channel Configuration (in the case of 0, the channel configuration is sent via an inband PCE) |
9 | Originality | 1 | set to 0 when encoding, ignore when decoding |
10 | Home | 1 | set to 0 when encoding, ignore when decoding |
11 | Copyrighted Stream | 1 | set to 0 when encoding, ignore when decoding |
12 | Copyrighted Start | 1 | set to 0 when encoding, ignore when decoding |
13 | Frame Length | 13 | this value must include 7 or 9 bytes of header length: FrameLength = (ProtectionAbsent == 1 ? 7 : 9) + size(AACFrame) |
14 | Buffer Fullness | 11 | buffer fullness |
15 | Number of AAC Frames | 2 | number of AAC frames (RDBs) in ADTS frame minus 1, for maximum compatibility always use 1 AAC frame per ADTS frame |
16 | CRC | 16 | CRC if protection absent is 0 |
AAC解码
在解码方面,使用了开源的FAAD,http://www.audiocoding.com/faad2.html
sdk解压缩后,docs目录有详细的api说明文档,主要用到的有以下几个:
NeAACDecHandle NEAACAPI NeAACDecOpen(void);
创建解码环境并返回一个句柄
void NEAACAPI NeAACDecClose(NeAACDecHandle hDecoder);
关闭解码环境
NeAACDecConfigurationPtr NEAACAPI NeAACDecGetCurrentConfiguration(NeAACDecHandle hDecoder);
获取当前解码器库的配置
unsigned char NEAACAPI NeAACDecSetConfiguration(NeAACDecHandle hDecoder, NeAACDecConfigurationPtr config);
为解码器库设置一个配置结构
long NEAACAPI NeAACDecInit(NeAACDecHandle hDecoder, unsigned char *buffer, unsigned long buffer_size, unsigned long *samplerate, unsigned char *channels);
初始化解码器库
void* NEAACAPI NeAACDecDecode(NeAACDecHandle hDecoder, NeAACDecFrameInfo *hInfo, unsigned char *buffer, unsigned long buffer_size);
解码AAC数据
对以上api做了简单封装,写了一个解码类,涵盖了FAAD库的基本用法,感兴趣的朋友可以看看
MyAACDecoder.h:
/**
*
* filename: MyAACDecoder.h
* summary: convert aac to wave
* author: caosiyang
* email: [email protected]
*
*/
#ifndef __MYAACDECODER_H__
#define __MYAACDECODER_H__
#include "Buffer.h"
#include "mytools.h"
#include "WaveFormat.h"
#include "faad.h"
#include <iostream>
using namespace std;
class MyAACDecoder {
public:
MyAACDecoder();
~MyAACDecoder();
int32_t Decode(char *aacbuf, uint32_t aacbuflen);
const char* WavBodyData() const {
return _mybuffer.Data();
}
uint32_t WavBodyLength() const {
return _mybuffer.Length();
}
const char* WavHeaderData() const {
return _wave_format.getHeaderData();
}
uint32_t WavHeaderLength() const {
return _wave_format.getHeaderLength();
}
private:
MyAACDecoder(const MyAACDecoder &dec);
MyAACDecoder& operator=(const MyAACDecoder &rhs);
//init AAC decoder
int32_t _init_aac_decoder(char *aacbuf, int32_t aacbuflen);
//destroy aac decoder
void _destroy_aac_decoder();
//parse AAC ADTS header, get frame length
uint32_t _get_frame_length(const char *aac_header) const;
//AAC decoder properties
NeAACDecHandle _handle;
unsigned long _samplerate;
unsigned char _channel;
Buffer _mybuffer;
WaveFormat _wave_format;
};
#endif /*__MYAACDECODER_H__*/
MyAACDecoder.cpp:
#include "MyAACDecoder.h"
MyAACDecoder::MyAACDecoder(): _handle(NULL), _samplerate(44100), _channel(2), _mybuffer(4096, 4096) {
}
MyAACDecoder::~MyAACDecoder() {
_destroy_aac_decoder();
}
int32_t MyAACDecoder::Decode(char *aacbuf, uint32_t aacbuflen) {
int32_t res = 0;
if (!_handle) {
if (_init_aac_decoder(aacbuf, aacbuflen) != 0) {
ERR1(":::: init aac decoder failed ::::");
return -1;
}
}
//clean _mybuffer
_mybuffer.Clean();
uint32_t donelen = 0;
uint32_t wav_data_len = 0;
while (donelen < aacbuflen) {
uint32_t framelen = _get_frame_length(aacbuf + donelen);
if (donelen + framelen > aacbuflen) {
break;
}
//decode
NeAACDecFrameInfo info;
void *buf = NeAACDecDecode(_handle, &info, (unsigned char*)aacbuf + donelen, framelen);
if (buf && info.error == 0) {
if (info.samplerate == 44100) {
//44100Hz
//src: 2048 samples, 4096 bytes
//dst: 2048 samples, 4096 bytes
uint32_t tmplen = info.samples * 16 / 8;
_mybuffer.Fill((const char*)buf, tmplen);
wav_data_len += tmplen;
} else if (info.samplerate == 22050) {
//22050Hz
//src: 1024 samples, 2048 bytes
//dst: 2048 samples, 4096 bytes
short *ori = (short*)buf;
short tmpbuf[info.samples * 2];
uint32_t tmplen = info.samples * 16 / 8 * 2;
for (int32_t i = 0, j = 0; i < info.samples; i += 2) {
tmpbuf[j++] = ori[i];
tmpbuf[j++] = ori[i + 1];
tmpbuf[j++] = ori[i];
tmpbuf[j++] = ori[i + 1];
}
_mybuffer.Fill((const char*)tmpbuf, tmplen);
wav_data_len += tmplen;
}
} else {
ERR1("NeAACDecDecode() failed");
}
donelen += framelen;
}
//generate Wave header
_wave_format.setSampleRate(_samplerate);
_wave_format.setChannel(_channel);
_wave_format.setSampleBit(16);
_wave_format.setBandWidth(_samplerate * 16 * _channel / 8);
_wave_format.setDataLength(wav_data_len);
_wave_format.setTotalLength(wav_data_len + 44);
_wave_format.GenerateHeader();
return 0;
}
uint32_t MyAACDecoder::_get_frame_length(const char *aac_header) const {
uint32_t len = *(uint32_t *)(aac_header + 3);
len = ntohl(len); //Little Endian
len = len << 6;
len = len >> 19;
return len;
}
int32_t MyAACDecoder::_init_aac_decoder(char* aacbuf, int32_t aacbuflen) {
unsigned long cap = NeAACDecGetCapabilities();
_handle = NeAACDecOpen();
if (!_handle) {
ERR1("NeAACDecOpen() failed");
_destroy_aac_decoder();
return -1;
}
NeAACDecConfigurationPtr conf = NeAACDecGetCurrentConfiguration(_handle);
if (!conf) {
ERR1("NeAACDecGetCurrentConfiguration() failed");
_destroy_aac_decoder();
return -1;
}
NeAACDecSetConfiguration(_handle, conf);
long res = NeAACDecInit(_handle, (unsigned char *)aacbuf, aacbuflen, &_samplerate, &_channel);
if (res < 0) {
ERR1("NeAACDecInit() failed");
_destroy_aac_decoder();
return -1;
}
//fprintf(stdout, "SampleRate = %d\n", _samplerate);
//fprintf(stdout, "Channel = %d\n", _channel);
//fprintf(stdout, ":::: init aac decoder done ::::\n");
return 0;
}
void MyAACDecoder::_destroy_aac_decoder() {
if (_handle) {
NeAACDecClose(_handle);
_handle = NULL;
}
}
1.ADTS是个啥
ADTS全称是(Audio Data Transport Stream),是AAC的一种十分常见的传输格式。
记得第一次做demux的时候,把AAC音频的ES流从FLV封装格式中抽出来送给硬件解码器时,不能播;保存到本地用pc的播放器播时,我靠也不能播。当时崩溃了,后来通过查找资料才知道。一般的AAC解码器都需要把AAC的ES流打包成ADTS的格式,一般是在AAC ES流前添加7个字节的ADTS header。也就是说你可以吧ADTS这个头看作是AAC的frameheader。
ADTS AAC | ||||||
ADTS_header | AAC ES | ADTS_header | AAC ES | ... | ADTS_header | AAC ES |
2.ADTS内容及结构
ADTS 头中相对有用的信息 采样率、声道数、帧长度。想想也是,我要是解码器的话,你给我一堆得AAC音频ES流我也解不出来。每一个带ADTS头信息的AAC流会清晰的告送解码器他需要的这些信息。
一般情况下ADTS的头信息都是7个字节,分为2部分:
adts_fixed_header();
adts_variable_header();
syncword :同步头 总是0xFFF, all bits must be 1,代表着一个ADTS帧的开始
ID:MPEG Version: 0 for MPEG-4, 1 for MPEG-2
Layer:always: '00'
profile:表示使用哪个级别的AAC,有些芯片只支持AAC LC 。在MPEG-2 AAC中定义了3种:
sampling_frequency_index:表示使用的采样率下标,通过这个下标在 Sampling Frequencies[ ]数组中查找得知采样率的值。
There are 13 supported frequencies:
- 0: 96000 Hz
- 1: 88200 Hz
- 2: 64000 Hz
- 3: 48000 Hz
- 4: 44100 Hz
- 5: 32000 Hz
- 6: 24000 Hz
- 7: 22050 Hz
- 8: 16000 Hz
- 9: 12000 Hz
- 10: 11025 Hz
- 11: 8000 Hz
- 12: 7350 Hz
- 13: Reserved
- 14: Reserved
- 15: frequency is written explictly
channel_configuration: 表示声道数
- 0: Defined in AOT Specifc Config
- 1: 1 channel: front-center
- 2: 2 channels: front-left, front-right
- 3: 3 channels: front-center, front-left, front-right
- 4: 4 channels: front-center, front-left, front-right, back-center
- 5: 5 channels: front-center, front-left, front-right, back-left, back-right
- 6: 6 channels: front-center, front-left, front-right, back-left, back-right, LFE-channel
- 7: 8 channels: front-center, front-left, front-right, side-left, side-right, back-left, back-right, LFE-channel
- 8-15: Reserved
frame_length : 一个ADTS帧的长度包括ADTS头和AAC原始流.
adts_buffer_fullness:0x7FF 说明是码率可变的码流
3.将AAC打包成ADTS格式
如果是通过嵌入式高清解码芯片做产品的话,一般情况的解码工作都是由硬件来完成的。所以大部分的工作是把AAC原始流打包成ADTS的格式,然后丢给硬件就行了。
通过对ADTS格式的了解,很容易就能把AAC打包成ADTS。我们只需得到封装格式里面关于音频采样率、声道数、元数据长度、aac格式类型等信息。然后在每个AAC原始流前面加上个ADTS头就OK了。
贴上ffmpeg中添加ADTS头的代码,就可以很清晰的了解ADTS头的结构:
- int ff_adts_write_frame_header(ADTSContext *ctx,
- uint8_t *buf, int size, int pce_size)
- {
- PutBitContext pb;
- init_put_bits(&pb, buf, ADTS_HEADER_SIZE);
- /* adts_fixed_header */
- put_bits(&pb, 12, 0xfff); /* syncword */
- put_bits(&pb, 1, 0); /* ID */
- put_bits(&pb, 2, 0); /* layer */
- put_bits(&pb, 1, 1); /* protection_absent */
- put_bits(&pb, 2, ctx->objecttype); /* profile_objecttype */
- put_bits(&pb, 4, ctx->sample_rate_index);
- put_bits(&pb, 1, 0); /* private_bit */
- put_bits(&pb, 3, ctx->channel_conf); /* channel_configuration */
- put_bits(&pb, 1, 0); /* original_copy */
- put_bits(&pb, 1, 0); /* home */
- /* adts_variable_header */
- put_bits(&pb, 1, 0); /* copyright_identification_bit */
- put_bits(&pb, 1, 0); /* copyright_identification_start */
- put_bits(&pb, 13, ADTS_HEADER_SIZE + size + pce_size); /* aac_frame_length */
- put_bits(&pb, 11, 0x7ff); /* adts_buffer_fullness */
- put_bits(&pb, 2, 0); /* number_of_raw_data_blocks_in_frame */
- flush_put_bits(&pb);
- return 0;
- }
- 顶
- 0
- 踩