Speex回波消除配置

Question

我正在制作安卓到安卓的VoIP (扬声器)应用程序，使用它的AudioRecord和AudioTrack类，以及通过NDK实现回波消除的Speex。我能够成功地从Speex的speex_echo_cancellation()函数中传递和检索数据，但是回显仍然存在。

这里是相关的android线程代码，它记录/发送和接收/播放音频：

//constructor
public MyThread(DatagramSocket socket, int frameSize, int filterLength){
  this.socket = socket;
  nativeMethod_initEchoState(frameSize, filterLength);
}

public void run(){

  short[] audioShorts, recvShorts, recordedShorts, filteredShorts;
  byte[] audioBytes, recvBytes;
  int shortsRead;
  DatagramPacket packet;

  //initialize recorder and player
  int samplingRate = 8000;
  int managerBufferSize = 2000;
  AudioTrack player = new AudioTrack(AudioManager.STREAM_MUSIC, samplingRate, AudioFormat.CHANNEL_OUT_MONO, AudioFormat.ENCODING_PCM_16BIT, managerBufferSize, AudioTrack.MODE_STREAM);
  recorder = new AudioRecord(MediaRecorder.AudioSource.MIC, samplingRate, AudioFormat.CHANNEL_IN_MONO, AudioFormat.ENCODING_PCM_16BIT, managerBufferSize);
  recorder.startRecording();
  player.play();

  //record first packet
  audioShorts = new short[1000];
  shortsRead = recorder.read(audioShorts, 0, audioShorts.length);

  //convert shorts to bytes to send
  audioBytes = new byte[shortsRead*2];
  ByteBuffer.wrap(audioBytes).order(ByteOrder.LITTLE_ENDIAN).asShortBuffer().put(audioShorts);

  //send bytes
  packet = new DatagramPacket(audioBytes, audioBytes.length);
  socket.send(packet);

  while (!this.isInterrupted()){

    //recieve packet/bytes (received audio data should have echo cancelled already)
    recvBytes = new byte[2000];
    packet = new DatagramPacket(recvBytes, recvBytes.length);
    socket.receive(packet);

    //convert bytes to shorts
    recvShorts = new short[packet.getLength()/2];
    ByteBuffer.wrap(packet.getData(), 0, packet.getLength()).order(ByteOrder.LITTLE_ENDIAN).asShortBuffer().get(recvShorts);

    //play shorts
    player.write(recvShorts, 0, recvShorts.length);

    //record shorts
    recordedShorts = new short[1000];
    shortsRead = recorder.read(recordedShorts, 0, recordedShorts.length);

    //send played and recorded shorts into speex, 
    //returning audio data with the echo removed
    filteredShorts = nativeMethod_speexEchoCancel(recordedShorts, recvShorts);

    //convert filtered shorts to bytes
    audioBytes = new byte[shortsRead*2];
    ByteBuffer.wrap(audioBytes).order(ByteOrder.LITTLE_ENDIAN).asShortBuffer().put(filteredShorts);

    //send off bytes
    packet = new DatagramPacket(audioBytes, audioBytes.length);
    socket.send(packet);                

  }//end of while loop 

}

这里是相关的NDK / JNI代码：

void nativeMethod_initEchoState(JNIEnv *env, jobject jobj, jint frameSize, jint filterLength){
  echo_state = speex_echo_state_init(frameSize, filterLength);
}

jshortArray nativeMethod_speexEchoCancel(JNIEnv *env, jobject jObj, jshortArray input_frame, jshortArray echo_frame){

  //create native shorts from java shorts
  jshort *native_input_frame = (*env)->GetShortArrayElements(env, input_frame, NULL);
  jshort *native_echo_frame = (*env)->GetShortArrayElements(env, echo_frame, NULL);

  //allocate memory for output data
  jint length = (*env)->GetArrayLength(env, input_frame);
  jshortArray temp = (*env)->NewShortArray(env, length);
  jshort *native_output_frame = (*env)->GetShortArrayElements(env, temp, 0);

  //call echo cancellation
  speex_echo_cancellation(echo_state, native_input_frame, native_echo_frame, native_output_frame);

  //convert native output to java layer output
  jshortArray output_shorts = (*env)->NewShortArray(env, length);
  (*env)->SetShortArrayRegion(env, output_shorts, 0, length, native_output_frame);

  //cleanup and return
  (*env)->ReleaseShortArrayElements(env, input_frame, native_input_frame, 0);
  (*env)->ReleaseShortArrayElements(env, echo_frame, native_echo_frame, 0);
  (*env)->ReleaseShortArrayElements(env, temp, native_output_frame, 0);
  return output_shorts;
}

这些代码运行良好，音频数据肯定是从android到android发送/接收/处理/播放的。假设音频采样率为8000 Hz，数据包大小为2000字节/ 1000短路，我发现需要1000 frameSize才能使播放的音频平滑。filterLength的大多数值(根据Speex，也称为尾长)将运行，但似乎对回波去除没有任何影响。

是否有人对AEC有足够的了解，可以为我提供一些关于实现或配置Speex的指导？感谢您的阅读。

Answer 1

您的代码是正确的，但在本机代码中缺少了一些内容，我修改了init方法，并在回波消除后添加了speex预处理，然后您的代码运行良好(我在windows中尝试过)，这里是本机代码。

#include <jni.h>
#include "speex/speex_echo.h"
#include "speex/speex_preprocess.h"
#include "EchoCanceller_jniHeader.h"
SpeexEchoState *st;
SpeexPreprocessState *den;

JNIEXPORT void JNICALL Java_speex_EchoCanceller_open
  (JNIEnv *env, jobject jObj, jint jSampleRate, jint jBufSize, jint jTotalSize)
{
     //init
     int sampleRate=jSampleRate;
     st = speex_echo_state_init(jBufSize, jTotalSize);
     den = speex_preprocess_state_init(jBufSize, sampleRate);
     speex_echo_ctl(st, SPEEX_ECHO_SET_SAMPLING_RATE, &sampleRate);
     speex_preprocess_ctl(den, SPEEX_PREPROCESS_SET_ECHO_STATE, st);
}

JNIEXPORT jshortArray JNICALL Java_speex_EchoCanceller_process
  (JNIEnv * env, jobject jObj, jshortArray input_frame, jshortArray echo_frame)
{
  //create native shorts from java shorts
  jshort *native_input_frame = (*env)->GetShortArrayElements(env, input_frame, NULL);
  jshort *native_echo_frame = (*env)->GetShortArrayElements(env, echo_frame, NULL);

  //allocate memory for output data
  jint length = (*env)->GetArrayLength(env, input_frame);
  jshortArray temp = (*env)->NewShortArray(env, length);
  jshort *native_output_frame = (*env)->GetShortArrayElements(env, temp, 0);

  //call echo cancellation
  speex_echo_cancellation(st, native_input_frame, native_echo_frame, native_output_frame);
  //preprocess output frame
  speex_preprocess_run(den, native_output_frame);

  //convert native output to java layer output
  jshortArray output_shorts = (*env)->NewShortArray(env, length);
  (*env)->SetShortArrayRegion(env, output_shorts, 0, length, native_output_frame);

  //cleanup and return
  (*env)->ReleaseShortArrayElements(env, input_frame, native_input_frame, 0);
  (*env)->ReleaseShortArrayElements(env, echo_frame, native_echo_frame, 0);
  (*env)->ReleaseShortArrayElements(env, temp, native_output_frame, 0);

  return output_shorts;   
}

JNIEXPORT void JNICALL Java_speex_EchoCanceller_close
  (JNIEnv *env, jobject jObj)
{
     //close
     speex_echo_state_destroy(st);
     speex_preprocess_state_destroy(den);
}

您可以在speex库的源代码(http://www.speex.org/downloads/)中找到有用的示例，如编码、解码、回波消除等。

Answer 2

您是否正确地对齐了远端信号(您称之为recv)和近端信号(您称之为记录)？总有一些回放/记录延迟需要考虑。这通常需要在一定时间内在环形缓冲器中缓冲远端信号。在个人电脑上，这通常是50-120毫秒。在Android上，我怀疑它要高得多。可能在150到400毫秒的范围内。我建议使用100毫秒的taillength和speex，并调整您的远端缓冲区的大小，直到AEC收敛。这些更改应该允许AEC收敛，而不需要包含预处理器，这在这里是不必要的。