I use SpeechRecognizer for implement a "speech-to-text" functional and result of her work is a text data:
Intent intent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);
intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE, Locale.US.toString());
intent.putExtra("android.speech.extra.EXTRA_ADDITIONAL_LANGUAGES", new String[]{});
SpeechRecognizer recognizer = SpeechRecognizer.createSpeechRecognizer(getApplicationContext());
recognizer.setRecognitionListener(new RecognitionListener() {
@Override
public void onReadyForSpeech(Bundle params) {}
@Override
public void onBeginningOfSpeech() {}
@Override
public void onRmsChanged(float rmsdB) {}
@Override
public void onBufferReceived(byte[] buffer) {}
@Override
public void onEndOfSpeech() {}
@Override
public void onError(int error) {}
@Override
public void onPartialResults(Bundle partialResults) {}
@Override
public void onEvent(int eventType, Bundle params) {}
@Override
public void onResults(Bundle results) {
String result = null;
ArrayList<String> arrOfResults = results.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
String command = arrOfResults.get(0);
}
});
recognizer.startListening(intent);
Is it possible to get a transcription of recognized speech instead of text using this method?
For example, as it was implemented in Google Translate:
Or, if necessary, use a different approach.
How can i do this? Thanks in advance. Regards...
The SpeechReocgnizer API only offers the "text" (normal orthographic text, I guess), and optionally the confidence scores, see: https://developer.android.com/reference/android/speech/RecognitionListener.html#onResults(android.os.Bundle)