使 SpeechRecognizer 在聆听时忽略大声播放的文本转语音

Question

我的实验代码如下（

compileSdk 34

，

minSdk 33

），只要单独考虑文本到语音和语音识别：，效果很好

package com.example.speechandspeak;

import android.Manifest;
import android.content.Intent;
import android.content.pm.PackageManager;
import android.os.Bundle;
import android.speech.RecognitionListener;
import android.speech.RecognizerIntent;
import android.speech.SpeechRecognizer;
import android.speech.tts.TextToSpeech;
import android.util.Log;
import android.widget.Toast;

import androidx.appcompat.app.AppCompatActivity;
import androidx.core.app.ActivityCompat;
import androidx.core.content.ContextCompat;

import java.util.ArrayList;
import java.util.Locale;

public class MainActivity extends AppCompatActivity implements RecognitionListener {

    private TextToSpeech tts;
    private SpeechRecognizer speechRecognizer;

    @Override
    protected void onCreate(Bundle savedInstanceState) {
        super.onCreate(savedInstanceState);
        setContentView(R.layout.activity_main);

        // Initialize TextToSpeech
        tts = new TextToSpeech(this, new TextToSpeech.OnInitListener() {
            @Override
            public void onInit(int status) {
                if (status == TextToSpeech.SUCCESS) {
                    int ttsLang = tts.setLanguage(Locale.US);
                    if (ttsLang == TextToSpeech.LANG_MISSING_DATA || ttsLang == TextToSpeech.LANG_NOT_SUPPORTED) {
                        Toast.makeText(MainActivity.this, "Language is not supported!", Toast.LENGTH_SHORT).show();
                    } else {
                        speakText();
                    }
                } else {
                    Toast.makeText(MainActivity.this, "TTS Initialization failed!", Toast.LENGTH_SHORT).show();
                }
            }
        });


        // Check if microphone permission is granted
        if (ContextCompat.checkSelfPermission(this, android.Manifest.permission.RECORD_AUDIO) != PackageManager.PERMISSION_GRANTED) {
            // Permission is not granted, request it
            ActivityCompat.requestPermissions(this, new String[]{Manifest.permission.RECORD_AUDIO}, 1);
        }
        // Initialize SpeechRecognizer
        speechRecognizer = SpeechRecognizer.createSpeechRecognizer(this);
        speechRecognizer.setRecognitionListener(this);
    }

    private void speakText() {
        Log.d(this.getLocalClassName(),  "Entered: " + Thread.currentThread().getStackTrace()[2].getMethodName());
        String message = getString(R.string.tts_message);
        tts.speak(message, TextToSpeech.QUEUE_FLUSH, null, null);

        // After speaking, initiate speech recognition
        Intent speechRecognizerIntent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
        speechRecognizer.startListening(speechRecognizerIntent);
    }

    @Override
    public void onReadyForSpeech(Bundle params) {
        Log.d(this.getLocalClassName(),  "Entered: " + Thread.currentThread().getStackTrace()[2].getMethodName());
    }

    @Override
    public void onBeginningOfSpeech() {
        Log.d(this.getLocalClassName(),  "Entered: " + Thread.currentThread().getStackTrace()[2].getMethodName());
    }

    @Override
    public void onRmsChanged(float rmsdB) {
        //Log.d(this.getLocalClassName(),  "Entered: " + Thread.currentThread().getStackTrace()[2].getMethodName());
    }

    @Override
    public void onBufferReceived(byte[] bytes) {
        Log.d(this.getLocalClassName(),  "Entered: " + Thread.currentThread().getStackTrace()[2].getMethodName());
    }

    @Override
    public void onEndOfSpeech() {
        Log.d(this.getLocalClassName(),  "Entered: " + Thread.currentThread().getStackTrace()[2].getMethodName());
    }

    @Override
    public void onError(int i) {
        Log.d(this.getLocalClassName(),  "Entered: " + Thread.currentThread().getStackTrace()[2].getMethodName() + "(" + i + ")");
    }

    @Override
    public void onEvent(int eventType, Bundle params) {
        Log.d(this.getLocalClassName(),  "Entered: " + Thread.currentThread().getStackTrace()[2].getMethodName());
    }

    @Override
    public void onPartialResults(Bundle partialResults) {
        Log.d(this.getLocalClassName(),  "Entered: " + Thread.currentThread().getStackTrace()[2].getMethodName());
    }

    @Override
    public void onResults(Bundle results) {
        Log.d(this.getLocalClassName(),  "Entered: " + Thread.currentThread().getStackTrace()[2].getMethodName());
        ArrayList<String> matches = results.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
        if (matches != null && !matches.isEmpty()) {
            Log.v(this.getLocalClassName(),  "Matches: " + matches);
            String text = matches.get(0).toLowerCase(); // Convert to lowercase for case-insensitive comparison
            if (text.equals("stop")) {
                if (tts.isSpeaking()) {
                    tts.stop();
                    speechRecognizer.stopListening(); // Stop listening for further commands
                    Toast.makeText(MainActivity.this, "Stopped!", Toast.LENGTH_SHORT).show();
                }
            }
        }
    }

    @Override
    protected void onDestroy() {
        super.onDestroy();
        if (tts != null) {
            tts.shutdown();
        }
    }
}

即例句（

“This is a demo of Speech Recognition and Text-to-Speech. Say stop! to quit.”）正在清晰播放，语音识别器已启动并正常工作，如图所示通过 Logcat 调试消息：

12:40:09.125 MainActivity              D  Entered: speakText
12:40:09.297                           D  Entered: onReadyForSpeech
12:40:09.761                           D  Entered: onBeginningOfSpeech
12:40:13.365                           D  Entered: onEndOfSpeech
12:40:13.394                           D  Entered: onResults
12:40:13.396                           V  Matches: [demonstration of speech recognition and text to speech say stop to quit]
12:40:14.524 ProfileInstaller          D  Installing profile for com.example.speechandspeak

但是，由于 voiceRecognizer 实际上在播放 TTS 的同时开始收听（故意，这是预期的测试用例），因此

onResults()

 仅识别 TTS 输出（

“语音识别和文本到语音的演示，说停止退出” ），忽略我在那段时间所说的一切。

我希望它专注于我的声音并忽略 TTS 输出。

我该如何实现这一目标？

我知道 Android 13+ 智能手机能够做到这一点，因为当我说

“嘿 Google” 当 TTS 大声播放时，我的语音正在被识别，TTS 输出暂停，Google Assistant 开始收听。 .

它是如何做到这一点的？

Answer 1

您需要使用应用了

AcousticEchoCanceler

效果的输入音频流。

SpeechRecognizer

 API 没有办法简单地打开它。您需要自己捕获输入音频，然后通过 

SpeechRecognizer

将其传递到

EXTRA_AUDIO_SOURCE

。

输入音频流需要以支持

AcousticEchoCanceler

 效果的方式进行配置。 

https://stackoverflow.com/a/38021196 有更多详细信息。

既然您询问了 Google Assistant：此类应用程序可能不使用

SpeechRecognizer

 API，因为它们试图检测特定短语（更专业的模型会更有效）。