Android快速集成微软语音服务（Azure认知服务）

小红妹

已于 2023-04-01 11:19:38 修改

阅读量2.1k

点赞数 2

分类专栏： Android 文章标签： android azure Azure认知服务微软语音服务文本合成语音

于 2023-03-18 15:05:05 首次发布

本文链接：https://blog.csdn.net/L_201607/article/details/129636431

版权

Android 专栏收录该内容

19 篇文章 0 订阅

订阅专栏

在网上溜了一圈，发现使用微软语音服务（Azure）的文章好少，为之感叹，在国内，百度语音、讯飞语音算是前沿语音技术，使用的公司和人自然不少，不过，在国际语言，小语种这块，还需要努力。刚开始，我也想使用百度语音翻译来着，后面发现集成好麻烦，API请求参数看懵逼了，不要友好，讯飞语音也想要集成了，看了一些demo，仔看看价格，和百度差不多，一直没动手集成，直到后面看到网上说白嫖微软语音合成文章后，大为受惊，操作一番，确实可以哈！一只白嫖一时爽，连续白嫖两周后，啊哈！网站上直接没有体验的入口了，就在不久前，也就是3月16号，俺一看，傻眼了，没了。
好吧！使用两周，感觉语音合成听着挺逼真的，那就注册一个账号，搞起来吧！至于费用什么的，后面再说。

一：注册一个微软账号

1、打开官网语音合成注册一个免费账号
如果打不开，可能需要科学上网，另外需要一个邮箱，最好是谷歌邮箱，其他邮箱如QQ邮箱没试过，不清楚，另外最最最最重要的是要有一张信用卡且支持Visa
在这里插入图片描述
2、开通认知服务中的语音Azure 服务
注册账号成功之后来到这个界面

点击左上角+号添加语音服务，获取密钥和位置/区域，推荐亚洲区（East Asia

二：集成语音SDK

1、GitHub示例代码
2、看官方文档，安装语音 SDK
跟着文档走，总结一下就是添加语音依赖库
在这里插入图片描述

implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.26.0'

3、文档中的示例我测试处理，下面放经过我优化调整后的代码，直接可用

import android.util.Log;
import com.microsoft.cognitiveservices.speech.*;
import com.xxx.config.Constants;

/**
 * @author 小红妹
 * @date 2023/3/16
 * @email L22~3535@163.com
 * @package com.xxx.speech
 * @describe  AzureSpeech
 * @copyright 
 */

public class SpeechSynthesis {

    private SpeechConfig speechConfig;
    private SpeechSynthesizer speechSynthesizer;
    private SpeechSynthesisResult speechSynthesisResult;

    public void azureSpeak() {
        // This example requires environment variables named "SPEECH_KEY" and "SPEECH_REGION"
        speechConfig = SpeechConfig.fromSubscription(Constants.SPEECH_KEY1, Constants.SPEECH_REGION);
        // Required for WordBoundary event sentences.
        speechConfig.setProperty(PropertyId.SpeechServiceResponse_RequestSentenceBoundary, "true");
        // Set either the `SpeechSynthesisVoiceName` or `SpeechSynthesisLanguage`.
        speechConfig.setSpeechSynthesisVoiceName(Constants.SPEECH_NAME);//"en-US-JennyNeural"

        String ssml = String.format("<speak version='1.0' xml:lang='en-US' xmlns='http://www.w3.org/2001/10/synthesis' xmlns:mstts='http://www.w3.org/2001/mstts'>"
                .concat(String.format("<voice name='%s'>", Constants.SPEECH_NAME))
                .concat("<mstts:viseme type='redlips_front'/>")
                .concat("The rainbow has seven colors: <bookmark mark='colors_list_begin'/>Red, orange, yellow, green, blue, indigo, and violet.<bookmark mark='colors_list_end'/>.")
                .concat("</voice>")
                .concat("</speak>"));

        assert(speechConfig != null);
       
        //将合成语音输出到当前活动输出设备（例如扬声器）
        AudioConfig audioConfig = AudioConfig.fromDefaultSpeakerOutput();
        speechSynthesizer = new SpeechSynthesizer(speechConfig, audioConfig);
        assert(speechSynthesizer != null);

        // Subscribe to events
        speechSynthesizer.BookmarkReached.addEventListener((o, e) -> {
            System.out.println("BookmarkReached event:");
            System.out.println("\tAudioOffset: " + ((e.getAudioOffset() + 5000) / 10000) + "ms");
            System.out.println("\tText: " + e.getText());
        });

        speechSynthesizer.SynthesisCanceled.addEventListener((o, e) -> {
            System.out.println("SynthesisCanceled event");
        });

        //ok
        speechSynthesizer.SynthesisCompleted.addEventListener((o, e) -> {
            SpeechSynthesisResult result = e.getResult();
            byte[] audioData = result.getAudioData();
            System.out.println("SynthesisCompleted event:");
            System.out.println("\tAudioData: " + audioData.length + " bytes");
            System.out.println("\tAudioDuration: " + result.getAudioDuration());
            result.close();
        });

        speechSynthesizer.SynthesisStarted.addEventListener((o, e) -> {
            System.out.println("SynthesisStarted event");
        });

        speechSynthesizer.Synthesizing.addEventListener((o, e) -> {
            SpeechSynthesisResult result = e.getResult();
            byte[] audioData = result.getAudioData();
            System.out.println("Synthesizing event:");
            System.out.println("\tAudioData: " + audioData.length + " bytes");
            result.close();
        });

        speechSynthesizer.VisemeReceived.addEventListener((o, e) -> {
            System.out.println("VisemeReceived event:");
            System.out.println("\tAudioOffset: " + ((e.getAudioOffset() + 5000) / 10000) + "ms");
            System.out.println("\tVisemeId: " + e.getVisemeId());
        });

        speechSynthesizer.WordBoundary.addEventListener((o, e) -> {
            System.out.println("WordBoundary event:");
            System.out.println("\tBoundaryType: " + e.getBoundaryType());
            System.out.println("\tAudioOffset: " + ((e.getAudioOffset() + 5000) / 10000) + "ms");
            System.out.println("\tDuration: " + e.getDuration());
            System.out.println("\tText: " + e.getText());
            System.out.println("\tTextOffset: " + e.getTextOffset());
            System.out.println("\tWordLength: " + e.getWordLength());
        });

        // Synthesize the SSML
        System.out.println("SSML to synthesize:");
        System.out.println(ssml);
        try {
            //speechSynthesisResult = speechSynthesizer.SpeakSsmlAsync(ssml).get();
            speechSynthesisResult = speechSynthesizer.SpeakText("おはようございます, 朝食を食べましょう!");

            assert(speechSynthesisResult != null);

            if (speechSynthesisResult.getReason() == ResultReason.SynthesizingAudioCompleted) {
                System.out.println("SynthesizingAudioCompleted result");
            }
            else if (speechSynthesisResult.getReason() == ResultReason.Canceled) {
                SpeechSynthesisCancellationDetails cancellation = SpeechSynthesisCancellationDetails.fromResult(speechSynthesisResult);
                System.out.println("CANCELED: Reason=" + cancellation.getReason());

                if (cancellation.getReason() == CancellationReason.Error) {
                    System.out.println("CANCELED: ErrorCode=" + cancellation.getErrorCode());
                    System.out.println("CANCELED: ErrorDetails=" + cancellation.getErrorDetails());
                    System.out.println("CANCELED: Did you set the speech resource key and region values?");
                }
            }

        } catch (Exception ex) {
            Log.e("SpeechSDKDemo", "unexpected " + ex.getMessage());
            assert(false);
        }

        System.exit(0);
    }

    //onDestroy
    public void closeSpeech() {
        // Release speech synthesizer and its dependencies
        speechSynthesizer.close();
        speechConfig.close();

    }

}