我已经成功创建了一个语音转文本应用程序，它能够基于识别关键字打开活动。目前，我需要单击一个按钮来启动语音转文本功能。我现在不想手动按下按钮，而是想使用连续监听器来触发按钮。
我一直在研究使用pocketsphinx，并添加了一个关键词“听命令”，一旦听到这个关键词，我希望自动按下按钮，然后是我可以添加到代码中的一系列命令。我不需要离线语音到文本等，因此我正在使用谷歌的语音到文本选项，但我计划使用 pocketsphinx 来触发谷歌的语音到文本功能。
下面是我从 pocketsphinx 部分修改的大部分代码：
public class PocketSphinxActivity extends Activity implements RecognitionListener {
/* Named searches allow to quickly reconfigure the decoder */
private static final String KWS_SEARCH = "wakeup";
private static final String FORECAST_SEARCH = "forecast";
private static final String DIGITS_SEARCH = "digits";
private static final String PHONE_SEARCH = "phones";
private static final String MENU_SEARCH = "menu";
/* Keyword we are looking for to activate menu */
private static final String KEYPHRASE = "listen to command"; //adjust this keyphrase!
private SpeechRecognizer recognizer;
private HashMap < String, Integer > captions;
@Override
public void onCreate(Bundle state) {
super.onCreate(state);
// Prepare the data for UI
captions = new HashMap < String, Integer > ();
captions.put(KWS_SEARCH, R.string.kws_caption);
captions.put(MENU_SEARCH, R.string.menu_caption);
captions.put(DIGITS_SEARCH, R.string.digits_caption);
captions.put(PHONE_SEARCH, R.string.phone_caption);
captions.put(FORECAST_SEARCH, R.string.forecast_caption);
setContentView(R.layout.main);
((TextView) findViewById(R.id.caption_text))
.setText("Preparing the recognizer");
// Recognizer initialization is a time-consuming and it involves IO,
// so we execute it in async task
new AsyncTask < Void, Void, Exception > () {
@Override
protected Exception doInBackground(Void...params) {
try {
Assets assets = new Assets(PocketSphinxActivity.this);
File assetDir = assets.syncAssets();
setupRecognizer(assetDir);
} catch (IOException e) {
return e;
}
return null;
}
@Override
protected void onPostExecute(Exception result) {
if (result != null) {
((TextView) findViewById(R.id.caption_text))
.setText("Failed to init recognizer " + result);
} else {
switchSearch(KWS_SEARCH);
}
}
}.execute();
}
@Override
public void onDestroy() {
super.onDestroy();
recognizer.cancel();
recognizer.shutdown();
}
/**
* In partial result we get quick updates about current hypothesis. In
* keyword spotting mode we can react here, in other modes we need to wait
* for final result in onResult.
*/
@Override
public void onPartialResult(Hypothesis hypothesis) {
if (hypothesis == null)
return;
String text = hypothesis.getHypstr();
if (text.equals(KEYPHRASE))
switchSearch(MENU_SEARCH);
else if (text.equals(DIGITS_SEARCH))
switchSearch(DIGITS_SEARCH);
else if (text.equals(PHONE_SEARCH))
switchSearch(PHONE_SEARCH);
else if (text.equals(FORECAST_SEARCH))
switchSearch(FORECAST_SEARCH);
else
((TextView) findViewById(R.id.result_text)).setText(text);
}
/**
* This callback is called when we stop the recognizer.
*/
@Override
public void onResult(Hypothesis hypothesis) {
((TextView) findViewById(R.id.result_text)).setText("");
if (hypothesis != null) {
String text = hypothesis.getHypstr();
makeText(getApplicationContext(), text, Toast.LENGTH_SHORT).show();
}
}
@Override
public void onBeginningOfSpeech() {}
/**
* We stop recognizer here to get a final result
*/
@Override
public void onEndOfSpeech() {
if (!recognizer.getSearchName().equals(KWS_SEARCH))
switchSearch(KWS_SEARCH);
}
private void switchSearch(String searchName) {
recognizer.stop();
// If we are not spotting, start listening with timeout (10000 ms or 10 seconds).
if (searchName.equals(KWS_SEARCH))
recognizer.startListening(searchName);
else
recognizer.startListening(searchName, 10000);
String caption = getResources().getString(captions.get(searchName));
((TextView) findViewById(R.id.caption_text)).setText(caption);
}
private void setupRecognizer(File assetsDir) throws IOException {
// The recognizer can be configured to perform multiple searches
// of different kind and switch between them
recognizer = defaultSetup()
.setAcousticModel(new File(assetsDir, "en-us-ptm"))
.setDictionary(new File(assetsDir, "cmudict-en-us.dict"))
// To disable logging of raw audio comment out this call (takes a lot of space on the device)
.setRawLogDir(assetsDir)
// Threshold to tune for keyphrase to balance between false alarms and misses
.setKeywordThreshold(1e-45 f)
// Use context-independent phonetic search, context-dependent is too slow for mobile
.setBoolean("-allphone_ci", true)
.getRecognizer();
recognizer.addListener(this);
/** In your application you might not need to add all those searches.
* They are added here for demonstration. You can leave just one.
*/
// Create keyword-activation search.
recognizer.addKeyphraseSearch(KWS_SEARCH, KEYPHRASE);
// Create grammar-based search for selection between demos
File menuGrammar = new File(assetsDir, "menu.gram");
recognizer.addGrammarSearch(MENU_SEARCH, menuGrammar);
// Create grammar-based search for digit recognition
File digitsGrammar = new File(assetsDir, "digits.gram");
recognizer.addGrammarSearch(DIGITS_SEARCH, digitsGrammar);
// Create language model search
File languageModel = new File(assetsDir, "weather.dmp");
recognizer.addNgramSearch(FORECAST_SEARCH, languageModel);
// Phonetic search
File phoneticModel = new File(assetsDir, "en-phone.dmp");
recognizer.addAllphoneSearch(PHONE_SEARCH, phoneticModel);
}
@Override
public void onError(Exception error) {
((TextView) findViewById(R.id.caption_text)).setText(error.getMessage());
}
@Override
public void onTimeout() {
switchSearch(KWS_SEARCH);
}
我对大多数命令不感兴趣，我只是希望应用程序在打开后立即收听（它目前正在执行），并且只要有人说它Listen to command然后按下我设置了 id 的按钮bVoice
如果有人可以帮助我修改上面的代码，以便我知道要删除什么以及添加什么，将不胜感激。另请注意，如果有更简单的方法可以做到这一点，请随时分享（也不需要自定义关键字）。