2
Я хочу разработать распознаватель речи в Android. Я использовал this thread и this video, чтобы использовать распознавание речи в устройстве Android.
Вот мой код:
MainActivity.java:Переключение исключения нулевого указателя для поиска в Pocketsphinx Demo
package com.example.pocket_sphinx;
import edu.cmu.pocketsphinx.Hypothesis;
import edu.cmu.pocketsphinx.RecognitionListener;
import android.os.Bundle;
import android.app.Activity;
import java.io.File;
import java.io.IOException;
import java.util.HashMap;
import static android.widget.Toast.makeText;
import static edu.cmu.pocketsphinx.SpeechRecognizerSetup.defaultSetup;
import android.os.AsyncTask;
import android.util.Log;
import android.widget.TextView;
import android.widget.Toast;
import edu.cmu.pocketsphinx.Assets;
import edu.cmu.pocketsphinx.SpeechRecognizer;
public class MainActivity extends Activity implements RecognitionListener {
private static final String KWS_SEARCH = "wakeup";
private static final String DICTATION_SEARCH = "digits";
private static final String KEYPHRASE = "oh mighty computer";
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>();
setContentView(R.layout.activity_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(MainActivity.this);
File assetDir = assets.syncAssets();
setupRecognizer(assetDir);
recognizer.startListening(KWS_SEARCH);
} 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 onPartialResult(Hypothesis hypothesis) {
String text = hypothesis.getHypstr();
Log.d("Spoken text",text);
if (text.equals(KEYPHRASE))
switchSearch(DICTATION_SEARCH);
else
((TextView) findViewById(R.id.result_text)).setText(text);
}
@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() {
}
@Override
public void onEndOfSpeech() {
Log.d("end","In end of speech");
if (DICTATION_SEARCH.equals(recognizer.getSearchName()))
switchSearch(KWS_SEARCH);
}
private void switchSearch(String searchName) {
recognizer.stop();
recognizer.startListening(searchName);
String caption = getResources().getString(captions.get(searchName));
((TextView) findViewById(R.id.caption_text)).setText(caption);
}
private void setupRecognizer(File assetsDir) {
File modelsDir = new File(assetsDir, "models");
recognizer = defaultSetup()
.setAcousticModel(new File(modelsDir, "hmm/en-us"))
.setDictionary(new File(modelsDir, "dict/cmu07a.dic"))
.setRawLogDir(assetsDir).setKeywordThreshold(1e-20f)
//.setFloat("-beam", 1e-30f)
.getRecognizer();
recognizer.addListener(this);
// Create keyword-activation search.
recognizer.addKeyphraseSearch(KWS_SEARCH, KEYPHRASE);
// Create language model search.
File languageModel = new File(modelsDir, "lm/weather.dmp");
recognizer.addNgramSearch(DICTATION_SEARCH, languageModel);
}
}
На самом деле я понятия не имею, как его использовать.
после запуска, он бросает исключение во время выполнения. Я отправил LogCat моего кода:
03-08 14:02:53.040: I/cmusphinx(17309): INFO: ngram_search_fwdtree.c(99): 788 unique initial diphones
03-08 14:02:53.230: I/cmusphinx(17309): INFO: ngram_search_fwdtree.c(148): 0 root, 0 non-root channels, 58 single-phone words
03-08 14:02:53.250: I/cmusphinx(17309): INFO: ngram_search_fwdtree.c(186): Creating search tree
03-08 14:02:53.470: I/cmusphinx(17309): INFO: ngram_search_fwdtree.c(192): before: 0 root, 0 non-root channels, 58 single-phone words
03-08 14:02:55.630: I/cmusphinx(17309): INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 2230
03-08 14:02:55.630: I/cmusphinx(17309): INFO: ngram_search_fwdtree.c(339): after: 253 root, 2102 non-root channels, 13 single-phone words
03-08 14:02:55.630: I/cmusphinx(17309): INFO: ngram_search_fwdflat.c(157): fwdflat: min_ef_width = 4, max_sf_win = 25
03-08 14:02:57.130: W/dalvikvm(17309): threadid=2: spin on suspend #1 threadid=11 (pcf=0)
03-08 14:02:57.140: W/dalvikvm(17309): threadid=2: spin on suspend resolved in 1010 msec
03-08 14:02:57.150: D/-heap(17309): GC_CONCURRENT freed 417K, 8% free 7863K/8455K, paused 14ms+1015ms, total 1597ms
03-08 14:02:57.210: I/SpeechRecognizer(17309): Start recognition "wakeup"
03-08 14:02:57.390: I/cmusphinx(17309): INFO: pocketsphinx.c(863): Writing raw audio log file: /mnt/sdcard/Android/data/com.example.pocket_sphinx/files/sync/000000000.raw
03-08 14:02:57.890: I/SpeechRecognizer(17309): Stop recognition
03-08 14:02:57.890: I/SpeechRecognizer(17309): Start recognition "wakeup"
03-08 14:02:57.890: W/dalvikvm(17309): threadid=1: thread exiting with uncaught exception (group=0x41ab9450)
03-08 14:02:57.930: E/AndroidRuntime(17309): FATAL EXCEPTION: main
03-08 14:02:57.930: E/AndroidRuntime(17309): java.lang.NullPointerException
03-08 14:02:57.930: E/AndroidRuntime(17309): at com.example.pocket_sphinx.MainActivity.switchSearch(MainActivity.java:108)
03-08 14:02:57.930: E/AndroidRuntime(17309): at com.example.pocket_sphinx.MainActivity.access$2(MainActivity.java:105)
03-08 14:02:57.930: E/AndroidRuntime(17309): at com.example.pocket_sphinx.MainActivity$1.onPostExecute(MainActivity.java:67)
03-08 14:02:57.930: E/AndroidRuntime(17309): at com.example.pocket_sphinx.MainActivity$1.onPostExecute(MainActivity.java:1)
03-08 14:02:57.930: E/AndroidRuntime(17309): at android.os.AsyncTask.finish(AsyncTask.java:631)
03-08 14:02:57.930: E/AndroidRuntime(17309): at android.os.AsyncTask.access$600(AsyncTask.java:177)
03-08 14:02:57.930: E/AndroidRuntime(17309): at android.os.AsyncTask$InternalHandler.handleMessage(AsyncTask.java:644)
03-08 14:02:57.930: E/AndroidRuntime(17309): at android.os.Handler.dispatchMessage(Handler.java:99)
03-08 14:02:57.930: E/AndroidRuntime(17309): at android.os.Looper.loop(Looper.java:137)
03-08 14:02:57.930: E/AndroidRuntime(17309): at android.app.ActivityThread.main(ActivityThread.java:4802)
03-08 14:02:57.930: E/AndroidRuntime(17309): at java.lang.reflect.Method.invokeNative(Native Method)
03-08 14:02:57.930: E/AndroidRuntime(17309): at java.lang.reflect.Method.invoke(Method.java:511)
03-08 14:02:57.930: E/AndroidRuntime(17309): at com.android.internal.os.ZygoteInit$MethodAndArgsCaller.run(ZygoteInit.java:813)
03-08 14:02:57.930: E/AndroidRuntime(17309): at com.android.internal.os.ZygoteInit.main(ZygoteInit.java:580)
03-08 14:02:57.930: E/AndroidRuntime(17309): at dalvik.system.NativeStart.main(Native Method)
03-08 14:02:57.940: I/cmusphinx(17309): INFO: pocketsphinx.c(863): Writing raw audio log file: /mnt/sdcard/Android/data/com.example.pocket_sphinx/files/sync/000000001.raw
Реальная ошибка несколько строк выше в LogCat. Вам нужно разместить полный логарифм, а не его часть. –
@NikolayShmyrev Спасибо за внимание! Я изменил его – AFN
@NikolayShmyrev это приложение должно распознавать голос через микрофон или файл? – AFN