我想保存/记录Google识别服务用于语音转文本操作的音频（使用RecognizerIntent或SpeechRecognizer）。
我尝试了许多方法：
从RecognitionListener的onBufferReceived：我知道，这不起作用，只是为了测试并且onBufferReceived从未被调用过（在带有JB 4.3的Galaxy Nexus上进行了测试）
使用媒体录制器：不起作用。它会破坏语音识别。麦克风仅允许一次操作
试图找到识别服务在执行语音转文本API之前保存临时音频文件的位置以复制它，但没有成功
我几乎绝望了，但我发现Google Keep应用程序正在做我需要做的事情！我使用logcat调试了一下保留应用程序，并且该应用程序也调用了“ RecognizerIntent.ACTION_RECOGNIZE_SPEECH”（就像我们开发人员所做的那样）来触发语音转文本。但是，Keep是如何保存音频的呢？它可能是隐藏的API吗？Google在“作弊”吗？
@Kaarel的答案几乎非常完整 - 生成的音频在intent.getData()中，可以使用ContentResolver读取。
不幸的是，返回的AMR文件质量较低 - 我无法找到获取高质量录音的方法。除“audio/AMR”之外的任何值在intent.getData()中返回null。
如果您找到获取高质量录音的方法，请发表评论或添加答案！
public void startSpeechRecognition() {
// Fire an intent to start the speech recognition activity.
Intent intent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
// secret parameters that when added provide audio url in the result
intent.putExtra("android.speech.extra.GET_AUDIO_FORMAT", "audio/AMR");
intent.putExtra("android.speech.extra.GET_AUDIO", true);
startActivityForResult(intent, "<some code you choose>");
}
// handle result of speech recognition
@Override
public void onActivityResult(int requestCode, int resultCode, Intent data) {
// the resulting text is in the getExtras:
Bundle bundle = data.getExtras();
ArrayList<String> matches = bundle.getStringArrayList(RecognizerIntent.EXTRA_RESULTS)
// the recording url is in getData:
Uri audioUri = data.getData();
ContentResolver contentResolver = getContentResolver();
InputStream filestream = contentResolver.openInputStream(audioUri);
// TODO: read audio file from inputstream
}
RecognizerIntent时设置了哪些额外内容，请实现一个应用程序来响应RecognizerIntent并打印出它所接收到的所有额外内容。您还可以安装Kõnele (http://kaljurand.github.io/K6nele/)，这是RecognizerIntent的实现。当Google Keep启动Kõnele时，长按扳手形状的设置图标。这会显示一些有关调用者的技术细节，并包括传入的额外内容。RecognizerIntent的调用者。intent.getData() 中而不是 getExtras() 中。结果是一个内容 URL，您需要使用 ContentResolver 打开它。 - Iftahpublic class MainActivity extends AppCompatActivity {
TextView textView;
ImageView imageView;
static int request = 1;
private static final int RECORDER_SAMPLERATE = 8000;
private static final int RECORDER_CHANNELS = AudioFormat.CHANNEL_IN_MONO;
private static final int RECORDER_AUDIO_ENCODING = AudioFormat.ENCODING_PCM_16BIT;
private AudioRecord recorder = null;
private Thread recordingThread = null;
private boolean isRecording = false;
private int[] mSampleRates = new int[]{8000, 11025, 22050, 44100};
int bufferSize;
@Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_main);
textView = findViewById(R.id.textView);
imageView = findViewById(R.id.mic);
int bufferSize = AudioRecord.getMinBufferSize(RECORDER_SAMPLERATE,
RECORDER_CHANNELS, RECORDER_AUDIO_ENCODING);
recorder = findAudioRecord();
if (ContextCompat.checkSelfPermission(this,
Manifest.permission.RECORD_AUDIO)
!= PackageManager.PERMISSION_GRANTED) {
ActivityCompat.requestPermissions(this,
new String[]{Manifest.permission.RECORD_AUDIO, Manifest.permission.WRITE_EXTERNAL_STORAGE, Manifest.permission.READ_EXTERNAL_STORAGE},
1234);
}
imageView.setOnClickListener(new View.OnClickListener() {
@Override
public void onClick(View v) {
Intent speech = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
speech.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL, RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);
speech.putExtra(RecognizerIntent.EXTRA_PROMPT, "Speak to Text");
if (ContextCompat.checkSelfPermission(MainActivity.this,
Manifest.permission.RECORD_AUDIO)
== PackageManager.PERMISSION_GRANTED) {
startRecording();
startActivityForResult(speech, request);
}
}
});
textView.setOnClickListener(new View.OnClickListener() {
@Override
public void onClick(View v) {
stopRecording();
}
});
}
@Override
protected void onActivityResult(int requestCode, int resultCode, @Nullable Intent data) {
super.onActivityResult(requestCode, resultCode, data);
if (requestCode == request && resultCode == RESULT_OK) {
stopRecording();
ArrayList<String> dataa = data.getStringArrayListExtra(RecognizerIntent.EXTRA_RESULTS);
textView.setText(dataa.get(0).toString());
}
}
int BufferElements2Rec = 1024; // want to play 2048 (2K) since 2 bytes we use only 1024
int BytesPerElement = 2; // 2 bytes in 16bit format
private void startRecording() {
recorder.startRecording();
isRecording = true;
recordingThread = new Thread(new Runnable() {
public void run() {
writeAudioDataToFile();
}
}, "AudioRecorder Thread");
recordingThread.start();
}
@Override
public void onRequestPermissionsResult(int requestCode,
String permissions[], int[] grantResults) {
switch (requestCode) {
case 1234: {
if (grantResults.length > 0
&& grantResults[0] == PackageManager.PERMISSION_GRANTED) {
} else {
Log.d("TAG", "permission denied by user");
}
return;
}
}
}
private byte[] short2byte(short[] sData) {
int shortArrsize = sData.length;
byte[] bytes = new byte[shortArrsize * 2];
for (int i = 0; i < shortArrsize; i++) {
bytes[i * 2] = (byte) (sData[i] & 0x00FF);
bytes[(i * 2) + 1] = (byte) (sData[i] >> 8);
sData[i] = 0;
}
return bytes;
}
public AudioRecord findAudioRecord() {
for (int rate : mSampleRates) {
for (short audioFormat : new short[]{
AudioFormat.ENCODING_PCM_8BIT,
AudioFormat.ENCODING_PCM_16BIT}) {
for (short channelConfig : new short[]{
AudioFormat.CHANNEL_IN_MONO,
AudioFormat.CHANNEL_IN_STEREO}) {
try {
Log.d("Mic2", "Attempting rate " + rate
+ "Hz, bits: " + audioFormat
+ ", channel: " + channelConfig);
bufferSize = AudioRecord.getMinBufferSize(rate,
channelConfig, audioFormat);
AudioRecord recorder = new AudioRecord(
MediaRecorder.AudioSource.DEFAULT, rate,
channelConfig, audioFormat, bufferSize);
if (recorder.getState() == AudioRecord.STATE_INITIALIZED)
rate = rate;
return recorder;
} catch (Exception e) {
Log.e("TAG", rate + "Exception, keep trying.", e);
}
}
}
}
return null;
}
private void writeAudioDataToFile() {
String filePath = Environment.getExternalStorageDirectory().getAbsolutePath() + "/file.pcm";
short sData[] = new short[BufferElements2Rec];
FileOutputStream os = null;
try {
os = new FileOutputStream(filePath);
} catch (FileNotFoundException e) {
e.printStackTrace();
}
while (isRecording) {
recorder.read(sData, 0, BufferElements2Rec);
System.out.println("Short writing to file" + sData.toString());
try {
byte bData[] = short2byte(sData);
os.write(bData, 0, BufferElements2Rec * BytesPerElement);
} catch (IOException e) {
e.printStackTrace();
}
}
try {
os.close();
} catch (IOException e) {
e.printStackTrace();
}
}
private void stopRecording() {
if (null != recorder) {
isRecording = false;
recorder.stop();
recorder.release();
recorder = null;
recordingThread = null;
}
}
@Override
public boolean onKeyDown(int keyCode, KeyEvent event) {
if (keyCode == KeyEvent.KEYCODE_BACK) {
finish();
}
return super.onKeyDown(keyCode, event);
}
InputStream filestream = contentResolver.openInputStream(audioUri); byte[] buffer = new byte[filestream.available()]; filestream.read(buffer); OutputStream outStream = new FileOutputStream(audiofile); outStream.write(buffer);请确保你已经有了一个名为audiofile的文件描述符。 - aac