语音识别为文字

最新推荐文章于 2024-08-09 14:20:22 发布

HungryGoogle

最新推荐文章于 2024-08-09 14:20:22 发布

阅读量3k

点赞数

分类专栏： Android 人工智能文章标签：人工智能

本文链接：https://blog.csdn.net/moonshine99/article/details/79120421

版权

Android 同时被 2 个专栏收录

11 篇文章 1 订阅

订阅专栏

人工智能

2 篇文章 0 订阅

订阅专栏

转载自 http://mp.blog.csdn.net/postedit/79120421

1、注册一个http://www.xfyun.cn/用户，申请SDK（免费的），主要是语音听写（就是语音转文字），http://www.xfyun.cn/services/voicedictation

2、下载SDK，注意自己的appid只能用自己的sdk，否则会创建语音识别接口失败

3、创建自己的android工程

参考我的代码 github https://github.com/HungryGoogle/LeeVoice2WordDemo

4、增加权限

    <uses-permission android:name="android.permission.RECORD_AUDIO" />
    <uses-permission android:name="android.permission.INTERNET" />
    <uses-permission android:name="android.permission.ACCESS_NETWORK_STATE" />
    <uses-permission android:name="android.permission.ACCESS_WIFI_STATE" />
    <uses-permission android:name="android.permission.CHANGE_NETWORK_STATE" />
    <uses-permission android:name="android.permission.READ_PHONE_STATE" />
    <uses-permission android:name="android.permission.ACCESS_FINE_LOCATION" />
    <uses-permission android:name="android.permission.READ_CONTACTS" />
    <uses-permission android:name="android.permission.WRITE_EXTERNAL_STORAGE" />
    <uses-permission android:name="android.permission.WRITE_SETTINGS" />
    <uses-permission android:name="android.permission.READ_EXTERNAL_STORAGE" />
    <uses-permission android:name="android.permission.ACCESS_FINE_LOCATION" />
    <uses-permission android:name="android.permission.ACCESS_COARSE_LOCATION" />

5、增加一个识别的activity

import android.app.Activity;
import android.os.Bundle;
import android.util.Log;
import android.view.MotionEvent;
import android.view.View;
import android.view.View.OnClickListener;
import android.widget.Button;
import android.widget.TextView;

import com.google.gson.Gson;
import com.google.gson.reflect.TypeToken;
import com.iflytek.cloud.RecognizerListener;
import com.iflytek.cloud.RecognizerResult;
import com.iflytek.cloud.SpeechConstant;
import com.iflytek.cloud.SpeechError;
import com.iflytek.cloud.SpeechRecognizer;
import com.iflytek.cloud.SpeechUtility;

import java.util.List;

public class Voice2Word extends Activity {
    Button mButton;
    TextView mResultShowTextView;
    private String dictationResultStr;
    private RecognizerListener mRecoListener = new RecognizerListener() {
        // 听写结果回调接口(返回Json格式结果)；
        // 比如：{"sn":1,"ls":false,"bg":0,"ed":0,"ws":[{"bg":0,"cw":[{"sc":0.00,"w":"我"}]},{"bg":0,"cw":[{"sc":0.00,"w":"是"}]},{"bg":0,"cw":[{"sc":0.00,"w":"万里长城"}]}]}
        public void onResult(RecognizerResult results, boolean isLast) {
            Log.i("leeTest", "RecognizerResult ---> " + results.getResultString());
            if (!isLast) {
                dictationResultStr += results.getResultString() + ",";
            } else {
                dictationResultStr += results.getResultString() + "]";
            }

            // 如果是最后一个，进行解析
            if (isLast) {
                // 解析Json列表字符串
                Gson gson = new Gson();
                List<Voide2WordsResult> voide2WordsResultList = gson
                        .fromJson(dictationResultStr,
                                new TypeToken<List<Voide2WordsResult>>() {
                                }.getType());

                String finalResult = "";
                for (int i = 0; i < voide2WordsResultList.size() - 1; i++) {
                    finalResult += voide2WordsResultList.get(i)
                            .toString();
                }
                Log.i("leeTest", "last result ---> " + finalResult);
                mResultShowTextView.setText(finalResult);
            }
        }

        //会话发生错误回调接口
        public void onError(SpeechError error) {
            error.getPlainDescription(true); //获取错误码描述
        }

        @Override
        public void onVolumeChanged(int i, byte[] bytes) {

        }

        //开始录音
        public void onBeginOfSpeech() {
        }

        //音量值0~30
        public void onVolumeChanged(int volume) {
        }

        //结束录音
        public void onEndOfSpeech() {
        }

        //扩展用接口
        public void onEvent(int eventType, int arg1, int arg2, Bundle obj) {
        }
    };
    private SpeechRecognizer mIat;

    @Override
    protected void onCreate(Bundle savedInstanceState) {
        super.onCreate(savedInstanceState);
        setContentView(R.layout.activity_speach2_word);
        SpeechUtility.createUtility(Voice2Word.this, SpeechConstant.APPID + "=5931728f");

        ButtonListener b = new ButtonListener();
        mButton = (Button) findViewById(R.id.button_voice_2_word);
        mButton.setOnClickListener(b);
        mButton.setOnTouchListener(b);
        mButton.setText("按住识别语音");
        mResultShowTextView = findViewById(R.id.id_show_voice_2_words_result);

        // 1 创建SpeechRecognizer对象，第二个参数：本地听写时传InitListener
        mIat = SpeechRecognizer.createRecognizer(Voice2Word.this, null);
        // 2 设置听写参数，详见《科大讯飞MSC API手册(Android)》SpeechConstant类
        mIat.setParameter(SpeechConstant.DOMAIN, "iat");
        mIat.setParameter(SpeechConstant.LANGUAGE, "zh_cn");
        mIat.setParameter(SpeechConstant.ACCENT, "mandarin ");
    }

    class ButtonListener implements OnClickListener, View.OnTouchListener {

        public void onClick(View v) {
            if (v.getId() == R.id.button_voice_2_word) {
                Log.d("leeTest", "cansal button ---> click");
            }
        }

        public boolean onTouch(View v, MotionEvent event) {
            if (v.getId() == R.id.button_voice_2_word) {
                if (event.getAction() == MotionEvent.ACTION_DOWN) {
                    Log.d("leeTest", "cansal button ---> ACTION_DOWN");
                    mButton.setText("录制并识别中...");

                    //3.开始听写
                    dictationResultStr = "[";
                    mIat.startListening(mRecoListener);
                }
                if (event.getAction() == MotionEvent.ACTION_UP) {
                    Log.d("leeTest", "cansal button ---> ACTION_UP");
                    mButton.setText("按住识别语音");


                    mIat.stopListening();
                }

            }
            return false;
        }
    }
}

6、增加结果解析类

/**
 * Created by Li on 2018/1/21.
 */

import java.util.List;

/**
 * 解析语音听写返回结果Json格式字符串的模板类（多重嵌套Json）
 * 语音识别结果Json数据格式（单条数据）：
 * {"sn":1,"ls":false,"bg":0,"ed":0,"ws":[{"bg":0,"cw":[{"sc":0.00,"w":"我"}]},{"bg":0,"cw":[{"sc":0.00,"w":"是"}]},{"bg":0,"cw":[{"sc":0.00,"w":"万里长城"}]}]}
 */
public class Voide2WordsResult {
    // 结果是json格式的，下面的都是json结果中的标签值
    private String sn;
    private String ls;
    private String bg;
    private String ed;

    private List<Words> ws;

    public static class Words {
        private String bg;
        private List<Cw> cw;

        public static class Cw {
            private String w;
            private String sc;

            public String getW() {
                return w;
            }

            public void setW(String w) {
                this.w = w;
            }

            public String getSc() {
                return sc;
            }

            public void setSc(String sc) {
                this.sc = sc;
            }

            @Override
            public String toString() {
                return w;
            }
        }

        public String getBg() {
            return bg;
        }

        public void setBg(String bg) {
            this.bg = bg;
        }

        public List<Cw> getCw() {
            return cw;
        }

        public void setCw(List<Cw> cw) {
            this.cw = cw;
        }

        @Override
        public String toString() {
            String result = "";
            for (Cw cwTmp : cw) {
                result += cwTmp.toString();
            }
            return result;
        }
    }

    public String getSn() {
        return sn;
    }

    public void setSn(String sn) {
        this.sn = sn;
    }

    public String getLs() {
        return ls;
    }

    public void setLs(String ls) {
        this.ls = ls;
    }

    public String getBg() {
        return bg;
    }

    public void setBg(String bg) {
        this.bg = bg;
    }

    public String getEd() {
        return ed;
    }

    public void setEd(String ed) {
        this.ed = ed;
    }

    public List<Words> getWs() {
        return ws;
    }

    public void setWs(List<Words> ws) {
        this.ws = ws;
    }

    @Override
    public String toString() {
        String result = "";
        for (Words wsTmp : ws) {
            result += wsTmp.toString();
        }
        return result;
    }
}

7、对应的配置文件

<?xml version="1.0" encoding="utf-8"?>
<LinearLayout xmlns:android="http://schemas.android.com/apk/res/android"
    android:layout_width="match_parent"
    android:layout_height="match_parent"
    android:gravity="center_horizontal"
    android:orientation="vertical">

    <Button
        android:id="@+id/button_voice_2_word"
        android:layout_width="wrap_content"
        android:layout_height="wrap_content"
        android:layout_margin="10dp"
        android:text="按住识别语音" />

    <TextView
        android:id="@+id/id_show_voice_2_words_result"
        android:layout_width="wrap_content"
        android:layout_height="wrap_content"
        android:layout_marginTop="20dp"
        android:text=" - 这里将展示结果 - " />

</LinearLayout>

8、copy自己的sdk和appid覆盖我的代码里面的，运行，安装后，一定要打开权限，demo没有做动态权限申请，录音等功能没有开启。

参考我的代码 github https://github.com/HungryGoogle/LeeVoice2WordDemo

备注：仅为个人开发者学习交流，如果转载或用于商业用途，后果自负。

请注明转载自 http://mp.blog.csdn.net/postedit/79120421