为什么需要声学回声消除呢？在一般的VOIP软件或视频会议系统中，假设我们只有A和B两个人在通话，首先，A的声音传给B，B然后用喇叭放出来，而这时B的MIC呢则会采集到喇叭放出来的声音，然后传回给A，如果这个传输的过程中时延足够大，A就会听到一个和自己刚才说过的话一样的声音，这就是回声，声学回声消除器的作用就是在B端对B采集到的声音进行处理，把采集到声音包含的A的声音去掉再传给A，这样，A就不会听到自己说过的话了。
声学回声消除的原理我就不说了，这在网上有很多文档，网上缺少的是实现，所以，我在这把一个开源的声学回声消除器介绍一下，希望对有些有人用，如果有人知道怎么把这消除器用的基于实时流的VOIP软件中，希望能一起分享一下。
这个声学回声消除器是一个著名的音频编解码器speex中的一部分，1.1.9版本后的回声消除器才起作用，以前版本的都不行，我用的也是这个版本，测试表明，用同一个模拟文件，它有效果比INTEL IPP库4.1版中的声学回声消除器的还要好。
先说编译。首先，从www.speex.org上下载speex1.1.9的源代码，解压，打开speex\win32\libspeex中的libspeex.dsw，这个工作区里有两个工程，一个是 libspeex，另一个是libspeex_dynamic。然后，将libspeex中的mdf.c文件添加到工程libspeex中，编译即可。
以下是我根据文档封装的一个类，里面有一个测试程序： //file name: speexEC.h
#ifndef SPEEX_EC_H
#define SPEEX_EC_H
#include <stdio.h>
#include <stdlib.h>
#include "speex/speex_echo.h"
#include "speex/speex_preprocess.h"
class CSpeexEC
{
public:
CSpeexEC();
~CSpeexEC();
void Init(int frame_size=160, int filter_length=1280, int sampling_rate=8000);
void DoAEC(short *mic, short *ref, short *out);
protected:
void Reset();
private:
bool m_bHasInit;
SpeexEchoState* m_pState;
SpeexPreprocessState* m_pPreprocessorState;
int m_nFrameSize;
int m_nFilterLen;
int m_nSampleRate;
float* m_pfNoise;
};
#endif
//fine name:speexEC.cpp
#include "SpeexEC.h"
CSpeexEC::CSpeexEC()
{
m_bHasInit = false;
m_pState = NULL;
m_pPreprocessorState = NULL;
m_nFrameSize = 160;
m_nFilterLen = 160*8;
m_nSampleRate = 8000;
m_pfNoise = NULL;
}
CSpeexEC::~CSpeexEC()
{
Reset();
}
void CSpeexEC::Init(int frame_size, int filter_length, int sampling_rate)
{
Reset();
if (frame_size<=0 || filter_length<=0 || sampling_rate<=0)
{
m_nFrameSize =160;
m_nFilterLen = 160*8;
m_nSampleRate = 8000;
}
else
{
m_nFrameSize =frame_size;
m_nFilterLen = filter_length;
m_nSampleRate = sampling_rate;
}
m_pState = speex_echo_state_init(m_nFrameSize, m_nFilterLen);
m_pPreprocessorState = speex_preprocess_state_init(m_nFrameSize, m_nSampleRate);
m_pfNoise = new float[m_nFrameSize+1];
m_bHasInit = true;
}
void CSpeexEC::Reset()
{
if (m_pState != NULL)
{
speex_echo_state_destroy(m_pState);
m_pState = NULL;
}
if (m_pPreprocessorState != NULL)
{
speex_preprocess_state_destroy(m_pPreprocessorState);
m_pPreprocessorState = NULL;
}
if (m_pfNoise != NULL)
{
delete []m_pfNoise;
m_pfNoise = NULL;
}
m_bHasInit = false;
}
void CSpeexEC:DoAEC(short* mic, short* ref, short* out)
{
if (!m_bHasInit)
return;
speex_echo_cancel(m_pState, mic, ref, out, m_pfNoise);
speex_preprocess(m_pPreprocessorState, (__int16 *)out, m_pfNoise);
}
可以看出，这个回声消除器类很简单，只要初始化一下就可以调用了。但是，要注意的是，传给回声消除器的两个声音信号，必须同步得非常的好，就是说，在B端，接收到A说的话以后，要把这些话音数据传给回声消除器做参考，然后再传给声卡，声卡再放出来，这有一段延时，这时，B再采集，然后传给回声消除器，与那个参考数据比较，从采集到的数据中把频域和参考数据相同的部分消除掉。如果传给消除器的两个信号同步得不好，即两个信号找不到频域相同的部分，就没有办法进行消除了。
测试程序：
#define NN 160
void main()
{
FILE* ref_fd, *mic_fd, *out_fd;
short ref[NN], mic[NN], out[NN];
ref_fd = fopen ("ref.pcm", "rb"); //打开参考文件，即要消除的声音
mic_fd = fopen ("mic.pcm", "rb");//打开mic采集到的声音文件，包含回声在里面
out_fd = fopen ("echo.pcm", "wb");//消除了回声以后的文件
CSpeexEC ec;
ec.Init();
while (fread(mic, 1, NN*2, mic_fd))
{
fread(ref, 1, NN*2, ref_fd);
ec.DoAEC(mic, ref, out);
fwrite(out, 1, NN*2, out_fd);
}
fclose(ref_fd);
fclose(mic_fd);
fclose(out_fd);
}
以上的程序是用文件来模拟回声和MIC，但在实时流中是大不一样的，在一般的VOIP软件中，接收对方的声音并传到声卡中播放是在一个线程中进行的，而采集本地的声音并传送到对方又是在另一个线程中进行的，而声学回声消除器在对采集到的声音进行回声消除的同时，还需要播放线程中的数据作为参考，而要同步这两个线程中的数据是非常困难的，因为稍稍有些不同步，声学回声消除器中的自适应滤波器就会发散，不但消除不了回声，还会破坏原始采集到的声音，使被破坏的声音难以分辨。我做过好多尝试，始终无法用软件来实现对这两个线程中的数据进行同步，导致实现失败，希望有经验的网友们一起分享一下这方面的经验。
示例代码：
Sample code
This section shows sample code for encoding and decoding speech using the Speex API. The commands can be used to encode and decode a file by calling:
% sampleenc in_file.sw | sampledec out_file.sw
where both files are raw (no header) files encoded at 16 bits per sample (in the machine natural endianness).
sampleenc.c
sampleenc takes a raw 16 bits/sample file, encodes it and outputs a Speex stream to stdout. Note that the packing used is NOT compatible with that of speexenc/speexdec.
#include <speex/speex.h>
#include <stdio.h>
#define FRAME_SIZE 160
int main(int argc, char **argv)
{
char *inFile;
FILE *fin;
short in[FRAME_SIZE];
float input[FRAME_SIZE];
char cbits[200];
int nbBytes;
void *state;
SpeexBits bits;
int i, tmp;
state = speex_encoder_init(&speex_nb_mode);
tmp=8;
speex_encoder_ctl(state, SPEEX_SET_QUALITY, &tmp);
inFile = argv[1];
fin = fopen(inFile, "r");
speex_bits_init(&bits);
while (1)
{
fread(in, sizeof(short), FRAME_SIZE, fin);
if (feof(fin))
break;
for (i=0;i<FRAME_SIZE;i++)
input[i]=in[i];
speex_bits_reset(&bits);
speex_encode(state, input, &bits);
nbBytes = speex_bits_write(&bits, cbits, 200);
fwrite(&nbBytes, sizeof(int), 1, stdout);
fwrite(cbits, 1, nbBytes, stdout);
}
speex_encoder_destroy(state);
speex_bits_destroy(&bits);
fclose(fin);
return 0;
}
sampledec.c
sampledec reads a Speex stream from stdin, decodes it and outputs it to a raw 16 bits/sample file. Note that the packing used is NOT compatible with that of speexenc/speexdec.
#include <speex/speex.h>
#include <stdio.h>
#define FRAME_SIZE 160
int main(int argc, char **argv)
{
char *outFile;
FILE *fout;
short out[FRAME_SIZE];
float output[FRAME_SIZE];
char cbits[200];
int nbBytes;
void *state;
SpeexBits bits;
int i, tmp;
state = speex_decoder_init(&speex_nb_mode);
tmp=1;
speex_decoder_ctl(state, SPEEX_SET_ENH, &tmp);
outFile = argv[1];
fout = fopen(outFile, "w");
speex_bits_init(&bits);
while (1)
{
fread(&nbBytes, sizeof(int), 1, stdin);
fprintf (stderr, "nbBytes: %d\n", nbBytes);
if (feof(stdin))
break;
fread(cbits, 1, nbBytes, stdin);
speex_bits_read_from(&bits, cbits, nbBytes);
speex_decode(state, &bits, output);
for (i=0;i<FRAME_SIZE;i++)
out[i]=output[i];
fwrite(out, sizeof(short), FRAME_SIZE, fout);
}
speex_decoder_destroy(state);
speex_bits_destroy(&bits);
fclose(fout);
return 0;
}
开源 H323 协议中封装的使用参考代码：
#include <ptlib.h>
#ifdef __GNUC__
#pragma implementation "speexcodec.h"
#endif
#include "speexcodec.h"
#include "h323caps.h"
#include "h245.h"
#include "rtp.h"
extern "C" {
#include "speex/libspeex/speex.h"
};
#define new PNEW
#define XIPH_COUNTRY_CODE 0xB5 // (181) Country code for United States
#define XIPH_T35EXTENSION 0
#define XIPH_MANUFACTURER_CODE 0x0026 // Allocated by Delta Inc
#define EQUIVALENCE_COUNTRY_CODE 9 // Country code for Australia
#define EQUIVALENCE_T35EXTENSION 0
#define EQUIVALENCE_MANUFACTURER_CODE 61 // Allocated by Australian Communications Authority, Oct 2000
#define SAMPLES_PER_FRAME 160
#define SPEEX_BASE_NAME "Speex"
#define SPEEX_NARROW2_H323_NAME SPEEX_BASE_NAME "Narrow-5.95k{sw}"
#define SPEEX_NARROW3_H323_NAME SPEEX_BASE_NAME "Narrow-8k{sw}"
#define SPEEX_NARROW4_H323_NAME SPEEX_BASE_NAME "Narrow-11k{sw}"
#define SPEEX_NARROW5_H323_NAME SPEEX_BASE_NAME "Narrow-15k{sw}"
#define SPEEX_NARROW6_H323_NAME SPEEX_BASE_NAME "Narrow-18.2k{sw}"
H323_REGISTER_CAPABILITY(SpeexNarrow2AudioCapability, SPEEX_NARROW2_H323_NAME);
H323_REGISTER_CAPABILITY(SpeexNarrow3AudioCapability, SPEEX_NARROW3_H323_NAME);
H323_REGISTER_CAPABILITY(SpeexNarrow4AudioCapability, SPEEX_NARROW4_H323_NAME);
H323_REGISTER_CAPABILITY(SpeexNarrow5AudioCapability, SPEEX_NARROW5_H323_NAME);
H323_REGISTER_CAPABILITY(SpeexNarrow6AudioCapability, SPEEX_NARROW6_H323_NAME);
#define XIPH_SPEEX_NARROW2_H323_NAME SPEEX_BASE_NAME "Narrow-5.95k(Xiph){sw}"
#define XIPH_SPEEX_NARROW3_H323_NAME SPEEX_BASE_NAME "Narrow-8k(Xiph){sw}"
#define XIPH_SPEEX_NARROW4_H323_NAME SPEEX_BASE_NAME "Narrow-11k(Xiph){sw}"
#define XIPH_SPEEX_NARROW5_H323_NAME SPEEX_BASE_NAME "Narrow-15k(Xiph){sw}"
#define XIPH_SPEEX_NARROW6_H323_NAME SPEEX_BASE_NAME "Narrow-18.2k(Xiph){sw}"
H323_REGISTER_CAPABILITY(XiphSpeexNarrow2AudioCapability, XIPH_SPEEX_NARROW2_H323_NAME);
H323_REGISTER_CAPABILITY(XiphSpeexNarrow3AudioCapability, XIPH_SPEEX_NARROW3_H323_NAME);
H323_REGISTER_CAPABILITY(XiphSpeexNarrow4AudioCapability, XIPH_SPEEX_NARROW4_H323_NAME);
H323_REGISTER_CAPABILITY(XiphSpeexNarrow5AudioCapability, XIPH_SPEEX_NARROW5_H323_NAME);
H323_REGISTER_CAPABILITY(XiphSpeexNarrow6AudioCapability, XIPH_SPEEX_NARROW6_H323_NAME);
/////////////////////////////////////////////////////////////////////////
static int Speex_Bits_Per_Second(int mode) {
void *tmp_coder_state;
int bitrate;
tmp_coder_state = speex_encoder_init(&speex_nb_mode);
speex_encoder_ctl(tmp_coder_state, SPEEX_SET_QUALITY, &mode);
speex_encoder_ctl(tmp_coder_state, SPEEX_GET_BITRATE, &bitrate);
speex_encoder_destroy(tmp_coder_state);
return bitrate;
}
static int Speex_Bytes_Per_Frame(int mode) {
int bits_per_frame = Speex_Bits_Per_Second(mode) / 50; // (20ms frame size)
return ((bits_per_frame+7)/8); // round up
}
OpalMediaFormat const OpalSpeexNarrow_5k95(OPAL_SPEEX_NARROW_5k95,
OpalMediaFormat::DefaultAudioSessionID,
RTP_DataFrame::DynamicBase,
TRUE, // Needs jitter
Speex_Bits_Per_Second(2),
Speex_Bytes_Per_Frame(2),
SAMPLES_PER_FRAME, // 20 milliseconds
OpalMediaFormat::AudioTimeUnits);
OpalMediaFormat const OpalSpeexNarrow_8k(OPAL_SPEEX_NARROW_8k,
OpalMediaFormat::DefaultAudioSessionID,
RTP_DataFrame::DynamicBase,
TRUE, // Needs jitter
Speex_Bits_Per_Second(3),
Speex_Bytes_Per_Frame(3),
SAMPLES_PER_FRAME, // 20 milliseconds
OpalMediaFormat::AudioTimeUnits);
OpalMediaFormat const OpalSpeexNarrow_11k(OPAL_SPEEX_NARROW_11k,
OpalMediaFormat::DefaultAudioSessionID,
RTP_DataFrame::DynamicBase,
TRUE, // Needs jitter
Speex_Bits_Per_Second(4),
Speex_Bytes_Per_Frame(4),
SAMPLES_PER_FRAME, // 20 milliseconds