Android应用程序中的语音检测

描述

我的应用程序从手机麦克风录音。 我正在使用android标准类（ android.media.AudioRecord ）来做到这一点。 应用程序有2个button“ 开始 ”和“ 停止 ”，当我按下开始button应用程序开始logging，当我按停止应用程序停止logging和给我回缓冲区，以.wav格式的语音数据。 一切正常。

问题

我想以这种方式改变我的应用程序，当应用程序开始工作时，它开始分析来自麦克风的声音，如果用户保持沉默的应用程序继续分析来自麦克风的收入声音，如果用户开始通话应用程序开始录制来自麦克风的声音然后用户完成通话应用程序停止logging，并给我回相同的缓冲区，语音数据.wav格式。

题

  1. 我如何检测到用户开始说话
  2. 我如何检测到用户停止说话

只需将此代码添加到您的应用程序中，您将会检测到用户何时开始说话以及何时停止。 

 public void onCreate(Bundle savedInstanceState) { super.onCreate(savedInstanceState); setContentView(R.layout.main); // Get the minimum buffer size required for the successful creation of an AudioRecord object. int bufferSizeInBytes = AudioRecord.getMinBufferSize( RECORDER_SAMPLERATE, RECORDER_CHANNELS, RECORDER_AUDIO_ENCODING ); // Initialize Audio Recorder. AudioRecord audioRecorder = new AudioRecord( MediaRecorder.AudioSource.MIC, RECORDER_SAMPLERATE, RECORDER_CHANNELS, RECORDER_AUDIO_ENCODING, bufferSizeInBytes ); // Start Recording. audioRecorder.startRecording(); int numberOfReadBytes = 0; byte audioBuffer[] = new byte[bufferSizeInBytes]; boolean recording = false; float tempFloatBuffer[] = new float[3]; int tempIndex = 0; int totalReadBytes = 0; byte totalByteBuffer[] = new byte[60 * 44100 * 2]; // While data come from microphone. while( true ) { float totalAbsValue = 0.0f; short sample = 0; numberOfReadBytes = audioRecorder.read( audioBuffer, 0, bufferSizeInBytes ); // Analyze Sound. for( int i=0; i<bufferSizeInBytes; i+=2 ) { sample = (short)( (audioBuffer[i]) | audioBuffer[i + 1] << 8 ); totalAbsValue += Math.abs( sample ) / (numberOfReadBytes/2); } // Analyze temp buffer. tempFloatBuffer[tempIndex%3] = totalAbsValue; float temp = 0.0f; for( int i=0; i<3; ++i ) temp += tempFloatBuffer[i]; if( (temp >=0 && temp <= 350) && recording == false ) { Log.i("TAG", "1"); tempIndex++; continue; } if( temp > 350 && recording == false ) { Log.i("TAG", "2"); recording = true; } if( (temp >= 0 && temp <= 350) && recording == true ) { Log.i("TAG", "Save audio to file."); // Save audio to file. String filepath = Environment.getExternalStorageDirectory().getPath(); File file = new File(filepath,"AudioRecorder"); if( !file.exists() ) file.mkdirs(); String fn = file.getAbsolutePath() + "/" + System.currentTimeMillis() + ".wav"; long totalAudioLen = 0; long totalDataLen = totalAudioLen + 36; long longSampleRate = RECORDER_SAMPLERATE; int channels = 1; long byteRate = RECORDER_BPP * RECORDER_SAMPLERATE * channels/8; totalAudioLen = totalReadBytes; totalDataLen = totalAudioLen + 36; byte finalBuffer[] = new byte[totalReadBytes + 44]; finalBuffer[0] = 'R'; // RIFF/WAVE header finalBuffer[1] = 'I'; finalBuffer[2] = 'F'; finalBuffer[3] = 'F'; finalBuffer[4] = (byte) (totalDataLen & 0xff); finalBuffer[5] = (byte) ((totalDataLen >> 8) & 0xff); finalBuffer[6] = (byte) ((totalDataLen >> 16) & 0xff); finalBuffer[7] = (byte) ((totalDataLen >> 24) & 0xff); finalBuffer[8] = 'W'; finalBuffer[9] = 'A'; finalBuffer[10] = 'V'; finalBuffer[11] = 'E'; finalBuffer[12] = 'f'; // 'fmt ' chunk finalBuffer[13] = 'm'; finalBuffer[14] = 't'; finalBuffer[15] = ' '; finalBuffer[16] = 16; // 4 bytes: size of 'fmt ' chunk finalBuffer[17] = 0; finalBuffer[18] = 0; finalBuffer[19] = 0; finalBuffer[20] = 1; // format = 1 finalBuffer[21] = 0; finalBuffer[22] = (byte) channels; finalBuffer[23] = 0; finalBuffer[24] = (byte) (longSampleRate & 0xff); finalBuffer[25] = (byte) ((longSampleRate >> 8) & 0xff); finalBuffer[26] = (byte) ((longSampleRate >> 16) & 0xff); finalBuffer[27] = (byte) ((longSampleRate >> 24) & 0xff); finalBuffer[28] = (byte) (byteRate & 0xff); finalBuffer[29] = (byte) ((byteRate >> 8) & 0xff); finalBuffer[30] = (byte) ((byteRate >> 16) & 0xff); finalBuffer[31] = (byte) ((byteRate >> 24) & 0xff); finalBuffer[32] = (byte) (2 * 16 / 8); // block align finalBuffer[33] = 0; finalBuffer[34] = RECORDER_BPP; // bits per sample finalBuffer[35] = 0; finalBuffer[36] = 'd'; finalBuffer[37] = 'a'; finalBuffer[38] = 't'; finalBuffer[39] = 'a'; finalBuffer[40] = (byte) (totalAudioLen & 0xff); finalBuffer[41] = (byte) ((totalAudioLen >> 8) & 0xff); finalBuffer[42] = (byte) ((totalAudioLen >> 16) & 0xff); finalBuffer[43] = (byte) ((totalAudioLen >> 24) & 0xff); for( int i=0; i<totalReadBytes; ++i ) finalBuffer[44+i] = totalByteBuffer[i]; FileOutputStream out; try { out = new FileOutputStream(fn); try { out.write(finalBuffer); out.close(); } catch (IOException e) { // TODO Auto-generated catch block e.printStackTrace(); } } catch (FileNotFoundException e1) { // TODO Auto-generated catch block e1.printStackTrace(); } //*/ tempIndex++; break; } // -> Recording sound here. Log.i( "TAG", "Recording Sound." ); for( int i=0; i<numberOfReadBytes; i++ ) totalByteBuffer[totalReadBytes + i] = audioBuffer[i]; totalReadBytes += numberOfReadBytes; //*/ tempIndex++; } }

检查这个链接 。

我以前回答过类似的问题，一种方法是使用logging上的线程和logging字节上的语音功率分析过程，有一个示例代码供您参考： http : //musicg.googlecode.com/files/musicg_android_demo。压缩

最好使用private static final int RECORDER_SAMPLERAT = 8000 ; 它对我有用，我认为这对你有帮助

当我用totalAbsValue += Math.abs( sample ) / (numberOfReadBytes/2) by totalAbsValue += (float)Math.abs( sample ) / ((float)numberOfReadBytes/(float)2)replacetotalAbsValue += Math.abs( sample ) / (numberOfReadBytes/2) by totalAbsValue += (float)Math.abs( sample ) / ((float)numberOfReadBytes/(float)2)那么它工作正常。

Interesting Posts