uni-app使用百度语音识别转文字

1. 准备

• 注册登录百度AI开放平台（http://ai.baidu.com/）
• 找到语音技术 - 应用列表，创建应用，填写相应信息，语音包名选择不需要
• 创建完成后，可以看到AppID、API Key、Secret Key

2. uni-app端开发

<template>
	<view>
		<button @tap="startRecord">开始录音button>
		<button @tap="endRecord">停止录音button>
		<button @tap="playVoice">播放录音button>
	view>
template>
<script>
	const recorderManager = uni.getRecorderManager();
	const innerAudioContext = uni.createInnerAudioContext();
	innerAudioContext.autoplay = true;
	var _this;
	
	export default {
		data() {
			return {
			}
		},
		onLoad() {
			_this = this;
			recorderManager.onStop(function(res) {
				console.log('recorder stop' + JSON.stringify(res));
				// 使用uni.uploadFile上传到服务器上，此时是mp3格式
			});
		},
		methods: {
			startRecord() {
				console.log('开始录音');
				recorderManager.start({
					sampleRate: 16000 // 必须设置是后台设置的参数，不然百度语音识别不了
				});
			},
			endRecord() {
				console.log('录音结束');
				_this = this;
				recorderManager.stop();
			},
			playVoice() {
				console.log('播放录音');

				if (this.voicePath) {
					innerAudioContext.src = this.voicePath;
					innerAudioContext.play();
				}
			}
		}
	}
script>

<style>
style>

3. java端开发

maven导入百度sdk，先将mp3转换为pcm，然后把pcm转换成二进制调用api

<dependency>
    <groupId>com.baidu.aipgroupId>
    <artifactId>java-sdkartifactId>
    <version>4.12.0version>
dependency>

<dependency>
    <groupId>com.googlecode.soundlibsgroupId>
    <artifactId>mp3spiartifactId>
    <version>1.9.5.4version>
dependency>

public class SpeechRecognitionUtil {

    //设置APPID/AK/SK
    public static final String APP_ID = "";
    public static final String API_KEY = "";
    public static final String SECRET_KEY = "";

    // 获取AipSpeech对象，建议单例使用
    public static AipSpeech getClient() {
        AipSpeech client = new AipSpeech(APP_ID, API_KEY, SECRET_KEY);
        // 可选：设置网络连接参数
        client.setConnectionTimeoutInMillis(2000);
        client.setSocketTimeoutInMillis(60000);
        return client;
    }

    // 语音识别（来自文件）
    public static JSONObject basicByFile(String path, String fileType) {
        AipSpeech client = getClient();
        return client.asr(path, fileType, 16000, null);
    }

    // 语音识别（来自二进制）
    public static JSONObject basicByByte(String filePath) throws IOException {
        AipSpeech client = getClient();
        byte[] data = Util.readFileByBytes(filePath);
        return client.asr(data, "pcm", 16000, null);
    }

    public static void main(String[] args) throws IOException {
        String mp3 = "D:/aa.mp3";
        String pcm = "D:/aa.pcm";
        MultiMediaUtil.MP3ConvertPcm(mp3,pcm);
        JSONObject jsonObject = basicByByte(pcm);
        System.out.println(jsonObject);
    }
}

public class MultiMediaUtil {

    // mp3转pcm
    public static boolean MP3ConvertPcm(String mp3filepath, String pcmfilepath){
        try {
            //获取文件的音频流，pcm的格式
            AudioInputStream audioInputStream = getPcmAudioInputStream(mp3filepath);
            //将音频转化为  pcm的格式保存下来
            AudioSystem.write(audioInputStream, AudioFileFormat.Type.WAVE, new File(pcmfilepath));
            return true;
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
            return false;
        }
    }

    /**
     * 获得pcm文件的音频流
     * @param mp3filepath
     * @return
     */
    private static AudioInputStream getPcmAudioInputStream(String mp3filepath) {
        File mp3 = new File(mp3filepath);
        AudioInputStream audioInputStream = null;
        AudioFormat targetFormat = null;
        try {
            AudioInputStream in = null;
            MpegAudioFileReader mp = new MpegAudioFileReader();
            in = mp.getAudioInputStream(mp3);
            AudioFormat baseFormat = in.getFormat();
            targetFormat = new AudioFormat(AudioFormat.Encoding.PCM_SIGNED, baseFormat.getSampleRate(), 16,
                    baseFormat.getChannels(), baseFormat.getChannels()*2, baseFormat.getSampleRate(), false);
            audioInputStream = AudioSystem.getAudioInputStream(targetFormat, in);
        } catch (Exception e) {
            e.printStackTrace();
        }
        return audioInputStream;
    }
}