android： AAC檔案解析

yangxi_001發表於2015-08-24
Android

AAC音訊格式分析

AAC音訊格式有ADIF和ADTS：

ADIF：Audio Data Interchange Format 音訊資料交換格式。這種格式的特徵是可以確定的找到這個音訊資料的開始，不需進行在音訊資料流中間開始的解碼，即它的解碼必須在明確定義的開始處進行。故這種格式常用在磁碟檔案中。

ADTS：Audio Data Transport Stream 音訊資料傳輸流。這種格式的特徵是它是一個有同步字的位元流，解碼可以在這個流中任何位置開始。它的特徵類似於mp3資料流格式。

簡單說，ADTS可以在任意幀解碼，也就是說它每一幀都有頭資訊。ADIF只有一個統一的頭，所以必須得到所有的資料後解碼。且這兩種的header的格式也是不同的，目前一般編碼後的和抽取出的都是ADTS格式的音訊流。

語音系統對實時性要求較高，基本是這樣一個流程，採集音訊資料，本地編碼，資料上傳，伺服器處理，資料下發，本地解碼

ADTS是幀序列，本身具備流特徵，在音訊流的傳輸與處理方面更加合適。

 

ADTS幀結構：

header

body

ADTS幀首部結構：

序號 域 長度（bits） 說明
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解碼

在解碼方面，使用了開源的FAAD，http://www.audiocoding.com/faad2.html

sdk解壓縮後，docs目錄有詳細的api說明文件，主要用到的有以下幾個：

NeAACDecHandle NEAACAPI NeAACDecOpen(void);

建立解碼環境並返回一個控制程式碼

void NEAACAPI NeAACDecClose(NeAACDecHandle hDecoder);

關閉解碼環境

NeAACDecConfigurationPtr NEAACAPI NeAACDecGetCurrentConfiguration(NeAACDecHandle hDecoder);

獲取當前解碼器庫的配置

unsigned char NEAACAPI NeAACDecSetConfiguration(NeAACDecHandle hDecoder, NeAACDecConfigurationPtr config);

為解碼器庫設定一個配置結構

long NEAACAPI NeAACDecInit(NeAACDecHandle hDecoder, unsigned char *buffer, unsigned long buffer_size, unsigned long *samplerate, unsigned char *channels);

初始化解碼器庫

void* NEAACAPI NeAACDecDecode(NeAACDecHandle hDecoder, NeAACDecFrameInfo *hInfo, unsigned char *buffer, unsigned long buffer_size);

解碼AAC資料



 



 



對以上api做了簡單封裝，寫了一個解碼類，涵蓋了FAAD庫的基本用法，感興趣的朋友可以看看



MyAACDecoder.h：




<span class="rem" style="color: rgb(0, 128, 0);">/**</span>


 *


<span class="rem" style="color: rgb(0, 128, 0);"> * filename: MyAACDecoder.h</span>


 * summary: convert aac to wave


<span class="rem" style="color: rgb(0, 128, 0);"> * author: caosiyang </span>


 * email: csy3228@gmail.com


<span class="rem" style="color: rgb(0, 128, 0);"> *</span>


 */


#ifndef __MYAACDECODER_H__


#define __MYAACDECODER_H__


 


 


#include <span class="str" style="color: rgb(0, 96, 128);">"Buffer.h"</span>


#include "mytools.h"


#include <span class="str" style="color: rgb(0, 96, 128);">"WaveFormat.h"</span>


#include "faad.h"


#include <iostream>


using namespace std;


 


 


<span class="kwrd" style="color: rgb(0, 0, 255);">class</span> MyAACDecoder {


public:


    MyAACDecoder();


    ~MyAACDecoder();


 


    int32_t Decode(char *aacbuf, uint32_t aacbuflen);


 


    const char* WavBodyData() const {


        <span class="kwrd" style="color: rgb(0, 0, 255);">return</span> _mybuffer.Data();


    }


 


    uint32_t WavBodyLength() const {


        <span class="kwrd" style="color: rgb(0, 0, 255);">return</span> _mybuffer.Length();


    }


 


    const char* WavHeaderData() const {


        <span class="kwrd" style="color: rgb(0, 0, 255);">return</span> _wave_format.getHeaderData();


 


    }


 


    uint32_t WavHeaderLength() <span class="kwrd" style="color: rgb(0, 0, 255);">const</span> {


        return _wave_format.getHeaderLength();


    }


 


<span class="kwrd" style="color: rgb(0, 0, 255);">private</span>:


    MyAACDecoder(const MyAACDecoder &dec);


    MyAACDecoder& <span class="kwrd" style="color: rgb(0, 0, 255);">operator</span>=(<span class="kwrd" style="color: rgb(0, 0, 255);">const</span> MyAACDecoder &rhs);


 


    <span class="rem" style="color: rgb(0, 128, 0);">//init AAC decoder</span>


    int32_t _init_aac_decoder(char *aacbuf, int32_t aacbuflen);


 


    //destroy aac decoder


    <span class="kwrd" style="color: rgb(0, 0, 255);">void</span> _destroy_aac_decoder();


 


    <span class="rem" style="color: rgb(0, 128, 0);">//parse AAC ADTS header, get frame length</span>


    uint32_t _get_frame_length(const char *aac_header) const;


 


    //AAC decoder properties


    NeAACDecHandle _handle;


    unsigned long _samplerate;


    unsigned <span class="kwrd" style="color: rgb(0, 0, 255);">char</span> _channel;


 


    Buffer _mybuffer;


    WaveFormat _wave_format;


};


 


 


#endif /*__MYAACDECODER_H__*/





 



MyAACDecoder.cpp：




#include <span class="str" style="color: rgb(0, 96, 128);">"MyAACDecoder.h"</span>


 


 


MyAACDecoder::MyAACDecoder(): _handle(NULL), _samplerate(44100), _channel(2), _mybuffer(4096, 4096) {


}


 


 


MyAACDecoder::~MyAACDecoder() {


    _destroy_aac_decoder();


}


 


 


int32_t MyAACDecoder::Decode(<span class="kwrd" style="color: rgb(0, 0, 255);">char</span> *aacbuf, uint32_t aacbuflen) {


    int32_t res = 0;


    <span class="kwrd" style="color: rgb(0, 0, 255);">if</span> (!_handle) {


        if (_init_aac_decoder(aacbuf, aacbuflen) != 0) {


            ERR1(<span class="str" style="color: rgb(0, 96, 128);">":::: init aac decoder failed ::::"</span>);


            return -1;


        }


    }


 


    //clean _mybuffer


    _mybuffer.Clean();


 


    uint32_t donelen = 0;


    uint32_t wav_data_len = 0;


    <span class="kwrd" style="color: rgb(0, 0, 255);">while</span> (donelen < aacbuflen) {


        uint32_t framelen = _get_frame_length(aacbuf + donelen);


 


        if (donelen + framelen > aacbuflen) {


            <span class="kwrd" style="color: rgb(0, 0, 255);">break</span>;


        }


 


        //decode


        NeAACDecFrameInfo info;


        void *buf = NeAACDecDecode(_handle, &info, (unsigned char*)aacbuf + donelen, framelen);


        <span class="kwrd" style="color: rgb(0, 0, 255);">if</span> (buf && info.error == 0) {


            if (info.samplerate == 44100) {


                <span class="rem" style="color: rgb(0, 128, 0);">//44100Hz</span>


                //src: 2048 samples, 4096 bytes


                <span class="rem" style="color: rgb(0, 128, 0);">//dst: 2048 samples, 4096 bytes</span>


                uint32_t tmplen = info.samples * 16 / 8;


                _mybuffer.Fill((<span class="kwrd" style="color: rgb(0, 0, 255);">const</span> <span class="kwrd" style="color: rgb(0, 0, 255);">char</span>*)buf, tmplen);


                wav_data_len += tmplen;


            } <span class="kwrd" style="color: rgb(0, 0, 255);">else</span> <span class="kwrd" style="color: rgb(0, 0, 255);">if</span> (info.samplerate == 22050) {


                //22050Hz


                <span class="rem" style="color: rgb(0, 128, 0);">//src: 1024 samples, 2048 bytes</span>


                //dst: 2048 samples, 4096 bytes


                <span class="kwrd" style="color: rgb(0, 0, 255);">short</span> *ori = (<span class="kwrd" style="color: rgb(0, 0, 255);">short</span>*)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;


            }


        } <span class="kwrd" style="color: rgb(0, 0, 255);">else</span> {


            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();


 


    <span class="kwrd" style="color: rgb(0, 0, 255);">return</span> 0;


}


 


 


uint32_t MyAACDecoder::_get_frame_length(<span class="kwrd" style="color: rgb(0, 0, 255);">const</span> <span class="kwrd" style="color: rgb(0, 0, 255);">char</span> *aac_header) <span class="kwrd" style="color: rgb(0, 0, 255);">const</span> {


    uint32_t len = *(uint32_t *)(aac_header + 3);


    len = ntohl(len); <span class="rem" style="color: rgb(0, 128, 0);">//Little Endian</span>


    len = len << 6;


    len = len >> 19;


    return len;


}


 


 


int32_t MyAACDecoder::_init_aac_decoder(char* aacbuf, int32_t aacbuflen) {


    unsigned <span class="kwrd" style="color: rgb(0, 0, 255);">long</span> cap = NeAACDecGetCapabilities();


    _handle = NeAACDecOpen();


    <span class="kwrd" style="color: rgb(0, 0, 255);">if</span> (!_handle) {


        ERR1("NeAACDecOpen() failed");


        _destroy_aac_decoder();


        return -1;


    }


 


    NeAACDecConfigurationPtr conf = NeAACDecGetCurrentConfiguration(_handle);


    if (!conf) {


        ERR1(<span class="str" style="color: rgb(0, 96, 128);">"NeAACDecGetCurrentConfiguration() failed"</span>);


        _destroy_aac_decoder();


        <span class="kwrd" style="color: rgb(0, 0, 255);">return</span> -1;


    }


    NeAACDecSetConfiguration(_handle, conf);


 


    <span class="kwrd" style="color: rgb(0, 0, 255);">long</span> res = NeAACDecInit(_handle, (unsigned <span class="kwrd" style="color: rgb(0, 0, 255);">char</span> *)aacbuf, aacbuflen, &_samplerate, &_channel);


    if (res < 0) {


        ERR1(<span class="str" style="color: rgb(0, 96, 128);">"NeAACDecInit() failed"</span>);


        _destroy_aac_decoder();


        <span class="kwrd" style="color: rgb(0, 0, 255);">return</span> -1;


    }


    <span class="rem" style="color: rgb(0, 128, 0);">//fprintf(stdout, "SampleRate = %d\n", _samplerate);</span>


    //fprintf(stdout, "Channel    = %d\n", _channel);


    <span class="rem" style="color: rgb(0, 128, 0);">//fprintf(stdout, ":::: init aac decoder done ::::\n");</span>


 


    <span class="kwrd" style="color: rgb(0, 0, 255);">return</span> 0;


}


 


 


<span class="kwrd" style="color: rgb(0, 0, 255);">void</span> MyAACDecoder::_destroy_aac_decoder() {


    if (_handle) {


        NeAACDecClose(_handle);


        _handle = NULL;


    }


}









相關文章