Android音频捕捉静音检测
我发现这个android代码当他/她开始说话时记录用户声音，当他/她停止时停止录音。 但问题是，录制停止很快。 如果要说两个字，就只记录第一个字。
如何改变下面的代码，使录音过程对短暂的沉默不那么敏感？
public void onCreate(Bundle savedInstanceState) { super.onCreate(savedInstanceState); setContentView(R.layout.main); final int RECORDER_BPP = 16; int RECORDER_SAMPLERATE = 8000; int RECORDER_CHANNELS = AudioFormat.CHANNEL_IN_MONO; int RECORDER_AUDIO_ENCODING = AudioFormat.ENCODING_PCM_16BIT; // 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 = 0 && temp 350 && recording == false) { Log.i("TAG", "2"); recording = true; } if ((temp >= 0 && temp > 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 Recording sound here. Log.i("TAG", "Recording Sound."); for (int i = 0; i < numberOfReadBytes; i++) totalByteBuffer[totalReadBytes + i] = audioBuffer[i]; totalReadBytes += numberOfReadBytes; // */ tempIndex++; } } 我不喜欢你写代码的方式。 使用我的。 您可以根据您的音量更改阈值variables。 在这个示例应用程序中没有按钮。 当你启动应用程序，它开始听，当你按下后退按钮，采集停止，文件存储在手机内存，文件夹AudioRecorder，每次运行一个新的文件。 读甚至评论和评论的代码。 注意：每次语音超过阈值时，语音都会附加到临时文件。 当你手动停止录音时，wav文件头被按回（wav文件是从临时文件创建的，具有一个新的唯一名称）。 如果每次显示声音时都需要创建一个新文件，可以根据自己的需要轻松修改，但是您应该经常通过临时文件保存。 如果您需要某种延迟，为了记录更多，即使没有声音（声音之后），只要在延迟时间内继续保存数据即可。 您可以创建延迟，计算自上次find峰值（表示语音存在）以来的经过时间（System.nanotime）。
不要忘记标记接受的解决方案（我测试过）。
package com.example.testaudiocapturewiththreshold; import android.os.Bundle; import android.app.Activity; import android.view.Menu; import java.io.File; import java.io.FileInputStream; import java.io.FileNotFoundException; import java.io.FileOutputStream; import java.io.IOException; import android.media.AudioFormat; import android.media.AudioRecord; import android.media.MediaRecorder; import android.os.AsyncTask; import android.os.Environment; import android.os.Handler; import android.util.Log; public class TestAudioCaptureWithThreshold extends Activity { private static final String TAG = TestAudioCaptureWithThreshold.class.getSimpleName(); private static final int RECORDER_BPP = 16; private static final String AUDIO_RECORDER_FILE_EXT_WAV = ".wav"; private static final String AUDIO_RECORDER_FOLDER = "AudioRecorder"; private static final String AUDIO_RECORDER_TEMP_FILE = "record_temp.raw"; FileOutputStream os = null; int bufferSize ; int frequency = 44100; //8000; int channelConfiguration = AudioFormat.CHANNEL_IN_MONO; int audioEncoding = AudioFormat.ENCODING_PCM_16BIT; boolean started = false; RecordAudio recordTask; short threshold=15000; boolean debug=false; @Override protected void onCreate(Bundle savedInstanceState) { Log.w(TAG, "onCreate"); super.onCreate(savedInstanceState); setContentView(R.layout.activity_test_audio_capture_with_threshold); startAquisition(); } @Override protected void onResume() { Log.w(TAG, "onResume"); super.onResume(); } @Override protected void onDestroy() { Log.w(TAG, "onDestroy"); stopAquisition(); super.onDestroy(); } public class RecordAudio extends AsyncTask { @Override protected Void doInBackground(Void... arg0) { Log.w(TAG, "doInBackground"); try { String filename = getTempFilename(); try { os = new FileOutputStream(filename); } catch (FileNotFoundException e) { e.printStackTrace(); } bufferSize = AudioRecord.getMinBufferSize(frequency, channelConfiguration, audioEncoding); AudioRecord audioRecord = new AudioRecord( MediaRecorder.AudioSource.MIC, frequency, channelConfiguration, audioEncoding, bufferSize); short[] buffer = new short[bufferSize]; audioRecord.startRecording(); while (started) { int bufferReadResult = audioRecord.read(buffer, 0,bufferSize); if(AudioRecord.ERROR_INVALID_OPERATION != bufferReadResult){ //check signal //put a threshold int foundPeak=searchThreshold(buffer,threshold); if (foundPeak>-1){ //found signal //record signal byte[] byteBuffer =ShortToByte(buffer,bufferReadResult); try { os.write(byteBuffer); } catch (IOException e) { e.printStackTrace(); } }else{//count the time //don't save signal } //show results //here, with publichProgress function, if you calculate the total saved samples, //you can optionally show the recorded file length in seconds: publishProgress(elsapsedTime,0); } } audioRecord.stop(); //close file try { os.close(); } catch (IOException e) { e.printStackTrace(); } copyWaveFile(getTempFilename(),getFilename()); deleteTempFile(); } catch (Throwable t) { t.printStackTrace(); Log.e("AudioRecord", "Recording Failed"); } return null; } //fine di doInBackground byte [] ShortToByte(short [] input, int elements) { int short_index, byte_index; int iterations = elements; //input.length; byte [] buffer = new byte[iterations * 2]; short_index = byte_index = 0; for(/*NOP*/; short_index != iterations; /*NOP*/) { buffer[byte_index] = (byte) (input[short_index] & 0x00FF); buffer[byte_index + 1] = (byte) ((input[short_index] & 0xFF00) >> 8); ++short_index; byte_index += 2; } return buffer; } int searchThreshold(short[]arr,short thr){ int peakIndex; int arrLen=arr.length; for (peakIndex=0;peakIndex=thr) || (arr[peakIndex]<=-thr)){ //se supera la soglia, esci e ritorna peakindex-mezzo kernel. return peakIndex; } } return -1; //not found } /* @Override protected void onProgressUpdate(Double... values) { DecimalFormat sf = new DecimalFormat("000.0000"); elapsedTimeTxt.setText(sf.format(values[0])); } */ private String getFilename(){ String filepath = Environment.getExternalStorageDirectory().getPath(); File file = new File(filepath,AUDIO_RECORDER_FOLDER); if(!file.exists()){ file.mkdirs(); } return (file.getAbsolutePath() + "/" + System.currentTimeMillis() + AUDIO_RECORDER_FILE_EXT_WAV); } private String getTempFilename(){ String filepath = Environment.getExternalStorageDirectory().getPath(); File file = new File(filepath,AUDIO_RECORDER_FOLDER); if(!file.exists()){ file.mkdirs(); } File tempFile = new File(filepath,AUDIO_RECORDER_TEMP_FILE); if(tempFile.exists()) tempFile.delete(); return (file.getAbsolutePath() + "/" + AUDIO_RECORDER_TEMP_FILE); } private void deleteTempFile() { File file = new File(getTempFilename()); file.delete(); } private void copyWaveFile(String inFilename,String outFilename){ FileInputStream in = null; FileOutputStream out = null; long totalAudioLen = 0; long totalDataLen = totalAudioLen + 36; long longSampleRate = frequency; int channels = 1; long byteRate = RECORDER_BPP * frequency * channels/8; byte[] data = new byte[bufferSize]; try { in = new FileInputStream(inFilename); out = new FileOutputStream(outFilename); totalAudioLen = in.getChannel().size(); totalDataLen = totalAudioLen + 36; WriteWaveFileHeader(out, totalAudioLen, totalDataLen, longSampleRate, channels, byteRate); while(in.read(data) != -1){ out.write(data); } in.close(); out.close(); } catch (FileNotFoundException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } } private void WriteWaveFileHeader( FileOutputStream out, long totalAudioLen, long totalDataLen, long longSampleRate, int channels, long byteRate) throws IOException { byte[] header = new byte[44]; header[0] = 'R'; // RIFF/WAVE header header[1] = 'I'; header[2] = 'F'; header[3] = 'F'; header[4] = (byte) (totalDataLen & 0xff); header[5] = (byte) ((totalDataLen >> 8) & 0xff); header[6] = (byte) ((totalDataLen >> 16) & 0xff); header[7] = (byte) ((totalDataLen >> 24) & 0xff); header[8] = 'W'; header[9] = 'A'; header[10] = 'V'; header[11] = 'E'; header[12] = 'f'; // 'fmt ' chunk header[13] = 'm'; header[14] = 't'; header[15] = ' '; header[16] = 16; // 4 bytes: size of 'fmt ' chunk header[17] = 0; header[18] = 0; header[19] = 0; header[20] = 1; // format = 1 header[21] = 0; header[22] = (byte) channels; header[23] = 0; header[24] = (byte) (longSampleRate & 0xff); header[25] = (byte) ((longSampleRate >> 8) & 0xff); header[26] = (byte) ((longSampleRate >> 16) & 0xff); header[27] = (byte) ((longSampleRate >> 24) & 0xff); header[28] = (byte) (byteRate & 0xff); header[29] = (byte) ((byteRate >> 8) & 0xff); header[30] = (byte) ((byteRate >> 16) & 0xff); header[31] = (byte) ((byteRate >> 24) & 0xff); header[32] = (byte) (channels * 16 / 8); // block align header[33] = 0; header[34] = RECORDER_BPP; // bits per sample header[35] = 0; header[36] = 'd'; header[37] = 'a'; header[38] = 't'; header[39] = 'a'; header[40] = (byte) (totalAudioLen & 0xff); header[41] = (byte) ((totalAudioLen >> 8) & 0xff); header[42] = (byte) ((totalAudioLen >> 16) & 0xff); header[43] = (byte) ((totalAudioLen >> 24) & 0xff); out.write(header, 0, 44); } } //Fine Classe RecordAudio (AsyncTask) @Override public boolean onCreateOptionsMenu(Menu menu) { getMenuInflater().inflate(R.menu.test_audio_capture_with_threshold, menu); return true; } public void resetAquisition() { Log.w(TAG, "resetAquisition"); stopAquisition(); //startButton.setText("WAIT"); startAquisition(); } public void stopAquisition() { Log.w(TAG, "stopAquisition"); if (started) { started = false; recordTask.cancel(true); } } public void startAquisition(){ Log.w(TAG, "startAquisition"); Handler handler = new Handler(); handler.postDelayed(new Runnable() { public void run() { //elapsedTime=0; started = true; recordTask = new RecordAudio(); recordTask.execute(); //startButton.setText("RESET"); } }, 500); } }
不要忘记添加清单文件的权限：
对于那些还没有find答案的人。当用户几秒钟没有说话时，可以检测到静音并停止录音。
为了计算用户是否已经停止说话，我们可以从录音的最后一秒开始读取数据，将其映射到一个数字，并将此数字与之前获得的数字进行比较。 是否变成语音输入中出现较长暂停的置信度分数（0-INF）。
按照这个链接，一切都在那里解释。 https://github.com/Kaljurand/speechutils/blob/master/app/src/main/java/ee/ioc/phon/android/speechutils/AbstractAudioRecorder.java感谢Kaljurand和他的精彩代码。
您可以在此链接中find整个项目。 https://github.com/Kaljurand/K6nele 。
这个post的代码正在工作。 但有一些问题。 事实是，这个记录突然中断了。 而声音正在玩的口吃。 为了解决我创建的conter silenceDegree。
看我的Kotlin代码：
var threshold: Short = 5000 val SILENCE_DEGREE = 15 //buffer size - need be fixed, established value for IOS compatibility val buffer = ShortArray(MIN_SIZE) var silenceDegree = 0 while (record) { val bytesRead = audioRecord?.read(buffer, 0, MIN_SIZE) if (bytesRead != null) { if (bytesRead > 0) { val foundPeak = searchThreshold(buffer, threshold) if (foundPeak == -1) { if (silenceDegree <= SILENCE_DEGREE) { silenceDegree++ } } else { silenceDegree = 0 } //stoping to send, only when counter became equals SILENCE_DEGREE if (silenceDegree < SILENCE_DEGREE) { //SEND USEFUL DATA handler.sendDataOnRecord(INSTANCE.shorts2Bytes(buffer)) } } else { if (bytesRead == AudioRecord.ERROR_INVALID_OPERATION) { // This can happen if there is already an active // AudioRecord (eg in another tab). record = false; } } }
阅读CAPTURE的这个文档
然后按照这几个链接，这可能会有助于找出你的错误。
http://www.devlper.com/2010/12/android-audio-recording-part-1/
http://www.devlper.com/2010/12/android-audio-recording-part-2/
最后确保你给你的应用程序需要的权限。 至少它需要RECORD_AUDIO和WRITE_EXTERNAL_STORAGE 。