想要使用html5网页实现语音识别,大概流程:用户点击录音按钮,进行语音录入,录入后上传语音,后台接收到请求后,会调用语音识别的方法,最后返回识别结果,前端接收到结果后再进行后续处理。
参考:https://blog.csdn.net/qq_33609401/article/details/78172080,这里面写得很详细,HZRecorder.js可以去这里复制。
所以技术上主要分为两个部分:语音获取、语音识别;
一、语音获取
在html上增加录音按钮,使用 HZRecorder.js,调用设备的录音功能,(注意:手机端浏览器需要有ssl证书(即网址协议为https)才能调用录音,有人说打包了就可以,没有ssl证书,打包了也会调用失败)
前端:
<!DOCTYPE html>
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<meta name="viewport" content="width=device-width,height=device-height, initial-scale=1.0, maximum-scale=1.0, user-scalable=0" />
<title></title>
</head>
<body>
<div>
<audio controls autoplay></audio>
<input onclick="startRecording()" type="button" value="录音" />
<input onclick="stopRecording()" type="button" value="停止" />
<input onclick="playRecording()" type="button" value="播放" />
<input onclick="uploadAudio()" type="button" value="提交" />
</div>
<script type="text/javascript" src="HZRecorder.js"></script>
<script>
var recorder;
var audio = document.querySelector('audio');
function startRecording() {
HZRecorder.get(function (rec) {
recorder = rec;
recorder.start();
});
}
function stopRecording() {
recorder.stop();
}
function playRecording() {
recorder.play(audio);
}
function uploadAudio() {
recorder.upload("http://localhost:8080/****/UploadVideoServlet", function (state, e) {
switch (state) {
case 'uploading':
break;
case 'ok':
alert("上传成功");
break;
case 'error':
alert("上传失败");
break;
case 'cancel':
alert("上传被取消");
break;
}
});
}
</script>
</body>
</html>
后台:在UploadVideoServlet中处理上传和调用语音识别代码。
@WebServlet("/UploadVideoServlet")
public class UploadVideoServlet extends HttpServlet {
private static final long serialVersionUID = 1L;
public UploadVideoServlet() {
super();
}
protected void doGet(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException {
response.getWriter().append("Served at: ").append(request.getContextPath());
this.doPost(request, response);
}
protected void doPost(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException {
// 消息提示
String message = "";
try {
DiskFileItemFactory factory = new DiskFileItemFactory();
ServletFileUpload upload = new ServletFileUpload(factory);
List<FileItem> list = upload.parseRequest(request);
for (FileItem item : list) {
// 调用语音识别方法
// Sample.main(item.get()); //百度
WebIAT.main(item.get()); //科大讯飞
message = "文件上传成功!";
}
} catch (Exception e) {
message = "文件上传失败!";
e.printStackTrace();
}
}
}
二、语音识别:使用科大讯飞或者百度提供的api实现。
(不论科大讯飞或者百度:(1) 都需要先去申请 APPID 、API_KEY,具体步骤去官网看看就知道了,(2)都提供了几种方式,我没有依次尝试)
1、科大讯飞示例:
参考 https://doc.xfyun.cn/rest_api/%E8%AF%AD%E9%9F%B3%E5%90%AC%E5%86%99.html
public class WebIAT {
// 听写webapi接口地址
private static final String WEBIAT_URL = "http://api.xfyun.cn/v1/service/v1/iat";
// 应用APPID(必须为webapi类型应用,并开通语音听写服务,参考帖子如何创建一个webapi应用:http://bbs.xfyun.cn/forum.php?mod=viewthread&tid=36481)
private static final String APPID = "*******";
// 接口密钥(webapi类型应用开通听写服务后,控制台--我的应用---语音听写---相应服务的apikey)
private static final String API_KEY = "*************************";
// 音频编码
private static final String AUE = "raw";
// 引擎类型
private static final String ENGINE_TYPE = "sms16k";
// 后端点(取值范围0-10000ms)
private static final String VAD_EOS = "10000";
/**
* 听写 WebAPI 调用示例程序
* @param args
* @throws IOException
*/
public static void main(byte[] bytes) throws IOException {
Map<String, String> header = buildHttpHeader();
//byte[] audioByteArray = FileUtil.read(AUDIO_PATH);
byte[] audioByteArray = bytes;
String audioBase64 = new String(Base64.encodeBase64(audioByteArray), "UTF-8");
String result = HttpUtil.doPost1(WEBIAT_URL, header, "audio=" + URLEncoder.encode(audioBase64, "UTF-8"));
System.out.println("听写 WebAPI 接口调用结果:" + result);
}
// 返回code为错误码时,请查询https://www.xfyun.cn/document/error-code解决方案
/**
* 组装http请求头
*/
private static Map<String, String> buildHttpHeader() throws UnsupportedEncodingException {
String curTime = System.currentTimeMillis() / 1000L + "";
String param = "{\"aue\":\""+AUE+"\""+",\"engine_type\":\"" + ENGINE_TYPE + "\""+",\"vad_eos\":\"" + VAD_EOS + "\"}";
String paramBase64 = new String(Base64.encodeBase64(param.getBytes("UTF-8")));
String checkSum = DigestUtils.md5Hex(API_KEY + curTime + paramBase64);
Map<String, String> header = new HashMap<String, String>();
header.put("Content-Type", "application/x-www-form-urlencoded; charset=utf-8");
header.put("X-Param", paramBase64);
header.put("X-CurTime", curTime);
header.put("X-CheckSum", checkSum);
header.put("X-Appid", APPID);
return header;
}
}
2、百度示例:
参考 https://ai.baidu.com/docs#/ASR-Online-Java-SDK/top
public class Sample {
private static final String serverURL = "http://vop.baidu.com/server_api";
private static String token = "";
//put your own params here
private static final String apiKey = "****************"; //改为自己的apiKey
private static final String secretKey = "*******************"; //改为自己的secretKey
private static final String cuid = "*******"; //唯一标识,可以写机器码
public static void main(byte[] bytes) throws Exception {
getToken();
method2(bytes);
}
private static void getToken() throws Exception {
String getTokenURL = "https://openapi.baidu.com/oauth/2.0/token?grant_type=client_credentials" +"&client_id=" + apiKey + "&client_secret=" + secretKey;
HttpURLConnection conn = (HttpURLConnection) new URL(getTokenURL).openConnection();
token = new JSONObject(printResponse(conn)).getString("access_token");
}
private static void method2(byte[] bytes) throws Exception {
HttpURLConnection conn = (HttpURLConnection) new URL(serverURL+ "?cuid=" + cuid + "&token=" + token).openConnection();
// add request header
conn.setRequestMethod("POST");
conn.setRequestProperty("Content-Type", "audio/wav; rate=16000");
conn.setDoInput(true);
conn.setDoOutput(true);
// send request
DataOutputStream wr = new DataOutputStream(conn.getOutputStream());
wr.write(bytes);
wr.flush();
wr.close();
printResponse(conn);
}
private static String printResponse(HttpURLConnection conn) throws Exception {
if (conn.getResponseCode() != 200) {
// request error
return "";
}
InputStream is = conn.getInputStream();
BufferedReader rd = new BufferedReader(new InputStreamReader(is));
String line;
StringBuffer response = new StringBuffer();
while ((line = rd.readLine()) != null) {
response.append(line);
response.append('\r');
}
rd.close();
System.out.println(new JSONObject(response.toString()).toString(4));
return response.toString();
}
转换结果示例:
拿到结果后,前端就可以进行后续处理了。
附: HZRecorder.js
(function (window) {
//兼容
window.URL = window.URL || window.webkitURL;
navigator.getUserMedia = navigator.getUserMedia || navigator.webkitGetUserMedia || navigator.mozGetUserMedia || navigator.msGetUserMedia;
var HZRecorder = function (stream, config) {
config = config || {};
config.sampleBits = config.sampleBits || 16; //采样数位 8, 16
config.sampleRate = config.sampleRate || (16000); //采样率(1/6 44100)
var context = new AudioContext();
var audioInput = context.createMediaStreamSource(stream);
var recorder = context.createScriptProcessor(4096, 1, 1);
var audioData = {
size: 0 //录音文件长度
, buffer: [] //录音缓存
, inputSampleRate: context.sampleRate //输入采样率
, inputSampleBits: 16 //输入采样数位 8, 16
, outputSampleRate: config.sampleRate //输出采样率
, oututSampleBits: config.sampleBits //输出采样数位 8, 16
, input: function (data) {
this.buffer.push(new Float32Array(data));
this.size += data.length;
}
, compress: function () { //合并压缩
//合并
var data = new Float32Array(this.size);
var offset = 0;
for (var i = 0; i < this.buffer.length; i++) {
data.set(this.buffer[i], offset);
offset += this.buffer[i].length;
}
//压缩
var compression = parseInt(this.inputSampleRate / this.outputSampleRate);
var length = data.length / compression;
var result = new Float32Array(length);
var index = 0, j = 0;
while (index < length) {
result[index] = data[j];
j += compression;
index++;
}
return result;
}
, encodeWAV: function () {
var sampleRate = Math.min(this.inputSampleRate, this.outputSampleRate);
var sampleBits = Math.min(this.inputSampleBits, this.oututSampleBits);
var bytes = this.compress();
var dataLength = bytes.length * (sampleBits / 8);
var buffer = new ArrayBuffer(44 + dataLength);
var data = new DataView(buffer);
var channelCount = 1;//单声道
var offset = 0;
var writeString = function (str) {
for (var i = 0; i < str.length; i++) {
data.setUint8(offset + i, str.charCodeAt(i));
}
}
// 资源交换文件标识符
writeString('RIFF'); offset += 4;
// 下个地址开始到文件尾总字节数,即文件大小-8
data.setUint32(offset, 36 + dataLength, true); offset += 4;
// WAV文件标志
writeString('WAVE'); offset += 4;
// 波形格式标志
writeString('fmt '); offset += 4;
// 过滤字节,一般为 0x10 = 16
data.setUint32(offset, 16, true); offset += 4;
// 格式类别 (PCM形式采样数据)
data.setUint16(offset, 1, true); offset += 2;
// 通道数
data.setUint16(offset, channelCount, true); offset += 2;
// 采样率,每秒样本数,表示每个通道的播放速度
data.setUint32(offset, sampleRate, true); offset += 4;
// 波形数据传输率 (每秒平均字节数) 单声道×每秒数据位数×每样本数据位/8
data.setUint32(offset, channelCount * sampleRate * (sampleBits / 8), true); offset += 4;
// 快数据调整数 采样一次占用字节数 单声道×每样本的数据位数/8
data.setUint16(offset, channelCount * (sampleBits / 8), true); offset += 2;
// 每样本数据位数
data.setUint16(offset, sampleBits, true); offset += 2;
// 数据标识符
writeString('data'); offset += 4;
// 采样数据总数,即数据总大小-44
data.setUint32(offset, dataLength, true); offset += 4;
// 写入采样数据
if (sampleBits === 8) {
for (var i = 0; i < bytes.length; i++, offset++) {
var s = Math.max(-1, Math.min(1, bytes[i]));
var val = s < 0 ? s * 0x8000 : s * 0x7FFF;
val = parseInt(255 / (65535 / (val + 32768)));
data.setInt8(offset, val, true);
}
} else {
for (var i = 0; i < bytes.length; i++, offset += 2) {
var s = Math.max(-1, Math.min(1, bytes[i]));
data.setInt16(offset, s < 0 ? s * 0x8000 : s * 0x7FFF, true);
}
}
return new Blob([data], { type: 'audio/wav' });
}
};
//开始录音
this.start = function () {
audioInput.connect(recorder);
recorder.connect(context.destination);
}
//停止
this.stop = function () {
recorder.disconnect();
}
//获取音频文件
this.getBlob = function () {
this.stop();
return audioData.encodeWAV();
}
//回放
this.play = function (audio) {
audio.src = window.URL.createObjectURL(this.getBlob());
}
//上传
this.upload = function (url, callback) {
var fd = new FormData();
fd.append("audioData", this.getBlob());
var xhr = new XMLHttpRequest();
if (callback) {
xhr.upload.addEventListener("progress", function (e) {
callback('uploading', e);
}, false);
xhr.addEventListener("load", function (e) {
callback('ok', e);
}, false);
xhr.addEventListener("error", function (e) {
callback('error', e);
}, false);
xhr.addEventListener("abort", function (e) {
callback('cancel', e);
}, false);
}
xhr.open("POST", url);
xhr.send(fd);
}
//音频采集
recorder.onaudioprocess = function (e) {
audioData.input(e.inputBuffer.getChannelData(0));
//record(e.inputBuffer.getChannelData(0));
}
};
//抛出异常
HZRecorder.throwError = function (message) {
alert(message);
throw new function () { this.toString = function () { return message; } }
}
//是否支持录音
HZRecorder.canRecording = (navigator.getUserMedia != null);
//获取录音机
HZRecorder.get = function (callback, config) {
if (callback) {
if (navigator.getUserMedia) {
navigator.getUserMedia(
{ audio: true } //只启用音频
, function (stream) {
var rec = new HZRecorder(stream, config);
callback(rec);
}
, function (error) {
console.log(error);
switch (error.code || error.name) {
case 'PERMISSION_DENIED':
case 'PermissionDeniedError':
HZRecorder.throwError('用户拒绝提供信息。');
break;
case 'NOT_SUPPORTED_ERROR':
case 'NotSupportedError':
HZRecorder.throwError('浏览器不支持硬件设备。');
break;
case 'MANDATORY_UNSATISFIED_ERROR':
case 'MandatoryUnsatisfiedError':
HZRecorder.throwError('无法发现指定的硬件设备。');
break;
default:
HZRecorder.throwError('无法打开麦克风。异常信息:' + (error.code || error.name));
break;
}
});
} else {
HZRecorder.throwErr('当前浏览器不支持录音功能。'); return;
}
}
}
window.HZRecorder = HZRecorder;
})(window);