diff --git a/Study-Vue-redis/ry-study-admin/pom.xml b/Study-Vue-redis/ry-study-admin/pom.xml
index 2c256a6..6aacf85 100644
--- a/Study-Vue-redis/ry-study-admin/pom.xml
+++ b/Study-Vue-redis/ry-study-admin/pom.xml
@@ -73,6 +73,13 @@
spring-boot-starter-websocket
+
+
+ com.baidu.aip
+ java-sdk
+ 4.16.18
+
+
diff --git a/Study-Vue-redis/ry-study-admin/src/main/java/com/ddnai/web/controller/study/BaiduSpeechService.java b/Study-Vue-redis/ry-study-admin/src/main/java/com/ddnai/web/controller/study/BaiduSpeechService.java
new file mode 100644
index 0000000..c482912
--- /dev/null
+++ b/Study-Vue-redis/ry-study-admin/src/main/java/com/ddnai/web/controller/study/BaiduSpeechService.java
@@ -0,0 +1,212 @@
+package com.ddnai.web.controller.study;
+
+import com.baidu.aip.speech.AipSpeech;
+import org.json.JSONObject;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import org.springframework.stereotype.Service;
+
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.IOException;
+import java.util.HashMap;
+
+/**
+ * 百度语音识别服务
+ * 主机访问百度云，内网设备通过主机使用语音识别
+ *
+ * @author ddnai
+ */
+@Service
+public class BaiduSpeechService
+{
+ private static final Logger log = LoggerFactory.getLogger(BaiduSpeechService.class);
+
+ // 百度语音识别配置
+ // 申请地址：https://console.bce.baidu.com/ai/#/ai/speech/overview/index
+ private static final String APP_ID = "7307076";
+ private static final String API_KEY = "RtL2IfV3FbLnVDDacRV6QDae";
+ private static final String SECRET_KEY = "NobJaGFov7II95fnFUBNGBk0Wm3fcNIB";
+
+ private AipSpeech client;
+
+ /**
+ * 初始化百度语音客户端
+ */
+ public BaiduSpeechService()
+ {
+ try
+ {
+ client = new AipSpeech(APP_ID, API_KEY, SECRET_KEY);
+ // 设置超时
+ client.setConnectionTimeoutInMillis(5000);
+ client.setSocketTimeoutInMillis(30000);
+ log.info("百度语音客户端初始化成功");
+ }
+ catch (Exception e)
+ {
+ log.error("百度语音客户端初始化失败", e);
+ }
+ }
+
+ /**
+ * 识别音频文件
+ *
+ * @param audioFile 音频文件（支持MP3、WAV、PCM等）
+ * @return 识别结果文本
+ */
+ public String recognizeAudio(File audioFile) throws IOException
+ {
+ return recognizeAudio(audioFile, getAudioFormat(audioFile.getName()));
+ }
+
+ /**
+ * 识别音频文件（指定格式）
+ *
+ * @param audioFile 音频文件
+ * @param format 音频格式（pcm/wav/mp3/m4a）
+ * @return 识别结果文本
+ */
+ public String recognizeAudio(File audioFile, String format) throws IOException
+ {
+ if (client == null)
+ {
+ throw new RuntimeException("百度语音客户端未初始化");
+ }
+
+ // 读取音频文件
+ byte[] audioData = readFileToBytes(audioFile);
+
+ // 计算音频时长（估算）
+ double durationSeconds = 0;
+ if ("wav".equals(format))
+ {
+ // WAV格式：16kHz, 单声道, 16位 = 32000 bytes/s
+ // 减去44字节的WAV文件头
+ durationSeconds = (audioData.length - 44) / 32000.0;
+ }
+ else if ("pcm".equals(format))
+ {
+ // PCM格式：无文件头
+ durationSeconds = audioData.length / 32000.0;
+ }
+
+ log.info("调用百度API识别音频 - 大小: {} bytes, 格式: {}, 估算时长: {}秒",
+ audioData.length, format, String.format("%.2f", durationSeconds));
+
+ // 检查音频时长
+ if (durationSeconds < 0.5)
+ {
+ log.warn("音频时长过短: {}秒，可能无法识别", String.format("%.2f", durationSeconds));
+ }
+ else if (durationSeconds > 10.0)
+ {
+ log.warn("音频时长过长: {}秒。百度短语音识别最佳时长为3-10秒，超过10秒可能只识别部分内容",
+ String.format("%.2f", durationSeconds));
+ }
+ else if (durationSeconds >= 2.0 && durationSeconds <= 10.0)
+ {
+ log.info("音频时长合适: {}秒（推荐范围：2-10秒）", String.format("%.2f", durationSeconds));
+ }
+
+ // 调用百度API
+ // format: 音频格式，支持 pcm/wav/mp3/m4a
+ // rate: 采样率，支持 8000/16000
+ HashMap options = new HashMap<>();
+ options.put("dev_pid", 1537); // 中文普通话识别
+
+ JSONObject result = client.asr(audioData, format, 16000, options);
+
+ log.info("百度API响应: {}", result.toString());
+
+ // 解析结果
+ int errNo = result.getInt("err_no");
+ if (errNo == 0)
+ {
+ // 成功
+ StringBuilder text = new StringBuilder();
+ if (result.has("result"))
+ {
+ org.json.JSONArray resultArray = result.getJSONArray("result");
+ log.info("识别结果数组长度: {}", resultArray.length());
+ for (int i = 0; i < resultArray.length(); i++)
+ {
+ String part = resultArray.getString(i);
+ log.info("识别片段[{}]: '{}'", i, part);
+ text.append(part);
+ }
+ }
+
+ String recognizedText = text.toString().trim();
+
+ if (recognizedText.isEmpty())
+ {
+ log.warn("百度API返回成功但识别结果为空 - 可能原因: 音频太短({}秒)、无声音或音量太小",
+ String.format("%.2f", durationSeconds));
+ }
+ else
+ {
+ log.info("识别成功: '{}', 长度: {}", recognizedText, recognizedText.length());
+ }
+
+ return recognizedText;
+ }
+ else
+ {
+ // 失败
+ String errMsg = result.optString("err_msg", "未知错误");
+ log.error("识别失败: err_no={}, err_msg={}", errNo, errMsg);
+ throw new RuntimeException("百度API识别失败: " + errMsg);
+ }
+ }
+
+ /**
+ * 读取文件为字节数组
+ */
+ private byte[] readFileToBytes(File file) throws IOException
+ {
+ try (FileInputStream fis = new FileInputStream(file))
+ {
+ byte[] data = new byte[(int) file.length()];
+ fis.read(data);
+ return data;
+ }
+ }
+
+ /**
+ * 根据文件名获取音频格式
+ */
+ private String getAudioFormat(String filename)
+ {
+ if (filename == null)
+ {
+ return "mp3";
+ }
+
+ String lowerName = filename.toLowerCase();
+ if (lowerName.endsWith(".wav"))
+ {
+ return "wav";
+ }
+ else if (lowerName.endsWith(".pcm"))
+ {
+ return "pcm";
+ }
+ else if (lowerName.endsWith(".m4a"))
+ {
+ return "m4a";
+ }
+ else
+ {
+ return "mp3"; // 默认MP3
+ }
+ }
+
+ /**
+ * 检查服务是否可用
+ */
+ public boolean isAvailable()
+ {
+ return client != null && !APP_ID.equals("你的APP_ID");
+ }
+}
diff --git a/Study-Vue-redis/ry-study-admin/src/main/java/com/ddnai/web/controller/study/VoiceSpeechController.java b/Study-Vue-redis/ry-study-admin/src/main/java/com/ddnai/web/controller/study/VoiceSpeechController.java
new file mode 100644
index 0000000..0902d91
--- /dev/null
+++ b/Study-Vue-redis/ry-study-admin/src/main/java/com/ddnai/web/controller/study/VoiceSpeechController.java
@@ -0,0 +1,222 @@
+package com.ddnai.web.controller.study;
+
+import java.io.File;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import org.springframework.beans.factory.annotation.Autowired;
+import org.springframework.web.bind.annotation.GetMapping;
+import org.springframework.web.bind.annotation.PostMapping;
+import org.springframework.web.bind.annotation.RequestMapping;
+import org.springframework.web.bind.annotation.RequestParam;
+import org.springframework.web.bind.annotation.RestController;
+import org.springframework.web.multipart.MultipartFile;
+import com.ddnai.common.core.controller.BaseController;
+import com.ddnai.common.core.domain.AjaxResult;
+
+/**
+ * 语音识别服务（使用百度云API）
+ * 主机访问百度云，内网设备通过主机使用语音识别
+ *
+ * @author ddnai
+ */
+@RestController
+@RequestMapping("/api/speech")
+public class VoiceSpeechController extends BaseController
+{
+ private static final Logger log = LoggerFactory.getLogger(VoiceSpeechController.class);
+
+ @Autowired
+ private BaiduSpeechService baiduSpeechService;
+
+ /**
+ * 健康检查接口
+ */
+ @GetMapping("/health")
+ public AjaxResult health()
+ {
+ try
+ {
+ boolean available = baiduSpeechService.isAvailable();
+
+ if (available)
+ {
+ log.info("百度语音服务正常");
+ return success("语音服务正常（百度云API）");
+ }
+ else
+ {
+ log.warn("百度语音服务未配置");
+ return error("语音服务未配置，请填写百度API密钥");
+ }
+ }
+ catch (Exception e)
+ {
+ log.error("语音服务检查失败", e);
+ return error("语音服务不可用: " + e.getMessage());
+ }
+ }
+
+ /**
+ * 语音识别接口
+ * 使用百度云API进行识别（主机访问百度云，内网设备通过主机使用）
+ */
+ @PostMapping("/recognize")
+ public AjaxResult recognize(
+ @RequestParam("audio") MultipartFile audioFile,
+ @RequestParam(value = "referenceText", required = false) String referenceText,
+ @RequestParam(value = "format", required = false, defaultValue = "wav") String format)
+ {
+ File tempInputFile = null;
+
+ try
+ {
+ log.info("收到语音识别请求 - 文件名: {}, 大小: {} bytes, 格式: {}, 参考文本: {}",
+ audioFile.getOriginalFilename(), audioFile.getSize(), format, referenceText);
+
+ // 保存上传的文件，使用指定的格式
+ tempInputFile = File.createTempFile("voice_", "." + format);
+ audioFile.transferTo(tempInputFile);
+
+ log.info("音频文件已保存: {}, 大小: {} bytes",
+ tempInputFile.getAbsolutePath(), tempInputFile.length());
+
+ // 调用百度API识别，传入格式参数
+ log.info("调用百度云API识别，格式: {}...", format);
+ String recognizedText = baiduSpeechService.recognizeAudio(tempInputFile, format);
+
+ if (recognizedText == null || recognizedText.isEmpty())
+ {
+ log.warn("未识别到有效语音");
+ return error("未识别到有效语音。请确保：1) 录音时长至少1秒；2) 说话声音清晰；3) 麦克风权限已授予");
+ }
+
+ log.info("识别成功: {}", recognizedText);
+
+ // 计算相似度评分
+ double score = calculateSimilarity(recognizedText, referenceText != null ? referenceText : "");
+ double pronunciationScore = Math.max(0, score - 5);
+ double fluencyScore = Math.max(0, score - 3);
+
+ log.info("相似度: {}分", score);
+
+ // 返回结果
+ java.util.Map data = new java.util.HashMap<>();
+ data.put("recognizedText", recognizedText);
+ data.put("score", score);
+ data.put("pronunciationScore", pronunciationScore);
+ data.put("fluencyScore", fluencyScore);
+ data.put("status", "completed");
+
+ return success(data);
+ }
+ catch (java.io.IOException e)
+ {
+ log.error("文件处理失败", e);
+ return error("文件处理失败: " + e.getMessage());
+ }
+ catch (Exception e)
+ {
+ log.error("语音识别请求失败", e);
+ return error("语音识别失败: " + e.getMessage());
+ }
+ finally
+ {
+ // 清理临时文件
+ if (tempInputFile != null && tempInputFile.exists())
+ {
+ if (tempInputFile.delete())
+ {
+ log.debug("临时文件已删除: {}", tempInputFile.getAbsolutePath());
+ }
+ else
+ {
+ log.warn("临时文件删除失败: {}", tempInputFile.getAbsolutePath());
+ }
+ }
+ }
+ }
+
+ /**
+ * 获取文件扩展名
+ */
+ private String getFileExtension(String filename)
+ {
+ if (filename == null || filename.isEmpty())
+ {
+ return "mp3";
+ }
+
+ int lastDotIndex = filename.lastIndexOf('.');
+ if (lastDotIndex > 0 && lastDotIndex < filename.length() - 1)
+ {
+ return filename.substring(lastDotIndex + 1);
+ }
+
+ return "mp3";
+ }
+
+ /**
+ * 计算文本相似度（0-100分）
+ */
+ private double calculateSimilarity(String text1, String text2)
+ {
+ if (text1 == null || text1.isEmpty() || text2 == null || text2.isEmpty())
+ {
+ return 0.0;
+ }
+
+ // 去除空格
+ text1 = text1.replaceAll("\\s+", "");
+ text2 = text2.replaceAll("\\s+", "");
+
+ if (text1.isEmpty() || text2.isEmpty())
+ {
+ return 0.0;
+ }
+
+ // 使用编辑距离计算相似度
+ int distance = levenshteinDistance(text1, text2);
+ int maxLength = Math.max(text1.length(), text2.length());
+
+ double similarity = (1.0 - (double) distance / maxLength) * 100;
+ return Math.round(similarity * 100.0) / 100.0; // 保留两位小数
+ }
+
+ /**
+ * 计算编辑距离（Levenshtein距离）
+ */
+ private int levenshteinDistance(String s1, String s2)
+ {
+ int len1 = s1.length();
+ int len2 = s2.length();
+
+ int[][] dp = new int[len1 + 1][len2 + 1];
+
+ for (int i = 0; i <= len1; i++)
+ {
+ dp[i][0] = i;
+ }
+
+ for (int j = 0; j <= len2; j++)
+ {
+ dp[0][j] = j;
+ }
+
+ for (int i = 1; i <= len1; i++)
+ {
+ for (int j = 1; j <= len2; j++)
+ {
+ if (s1.charAt(i - 1) == s2.charAt(j - 1))
+ {
+ dp[i][j] = dp[i - 1][j - 1];
+ }
+ else
+ {
+ dp[i][j] = Math.min(Math.min(dp[i - 1][j], dp[i][j - 1]), dp[i - 1][j - 1]) + 1;
+ }
+ }
+ }
+
+ return dp[len1][len2];
+ }
+}
diff --git a/baidu_speech_server.py b/baidu_speech_server.py
new file mode 100644
index 0000000..08bf938
--- /dev/null
+++ b/baidu_speech_server.py
@@ -0,0 +1,172 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+百度语音识别服务（超级简单，不需要ffmpeg）
+免费额度：每天50000次
+"""
+
+from flask import Flask, request, jsonify
+from flask_cors import CORS
+import base64
+import json
+from difflib import SequenceMatcher
+
+app = Flask(__name__)
+CORS(app)
+
+# 百度语音识别配置（需要申请）
+# 免费申请地址：https://console.bce.baidu.com/ai/#/ai/speech/overview/index
+BAIDU_APP_ID = "你的APP_ID" # ← 需要替换
+BAIDU_API_KEY = "你的API_KEY" # ← 需要替换
+BAIDU_SECRET_KEY = "你的SECRET_KEY" # ← 需要替换
+
+# 懒加载客户端
+asr_client = None
+
+def get_asr_client():
+ """获取百度语音识别客户端"""
+ global asr_client
+ if asr_client is None:
+ try:
+ from aip import AipSpeech
+ asr_client = AipSpeech(BAIDU_APP_ID, BAIDU_API_KEY, BAIDU_SECRET_KEY)
+ print("✓ 百度语音客户端初始化成功")
+ except ImportError:
+ print("✗ 未安装百度SDK，请运行: pip install baidu-aip")
+ return None
+ except Exception as e:
+ print(f"✗ 初始化失败: {str(e)}")
+ return None
+ return asr_client
+
+def recognize_audio_baidu(audio_data, format='mp3'):
+ """使用百度API识别音频"""
+ try:
+ client = get_asr_client()
+ if not client:
+ return None, "百度语音客户端未初始化"
+
+ # 百度API识别
+ result = client.asr(audio_data, format, 16000, {
+ 'dev_pid': 1537, # 中文普通话
+ })
+
+ if result['err_no'] == 0:
+ text = ''.join(result['result'])
+ return text, None
+ else:
+ return None, f"识别失败: {result.get('err_msg', '未知错误')}"
+
+ except Exception as e:
+ return None, str(e)
+
+def calculate_similarity(text1, text2):
+ """计算文本相似度（0-100分）"""
+ if not text1 or not text2:
+ return 0
+
+ text1 = text1.replace(" ", "")
+ text2 = text2.replace(" ", "")
+
+ if not text1 or not text2:
+ return 0
+
+ similarity = SequenceMatcher(None, text1, text2).ratio()
+ return round(similarity * 100, 2)
+
+@app.route('/api/speech/recognize', methods=['POST'])
+def recognize():
+ """语音识别接口"""
+ try:
+ # 检查文件
+ if 'audio' not in request.files:
+ return jsonify({
+ 'code': 400,
+ 'msg': '未上传音频文件'
+ }), 400
+
+ audio_file = request.files['audio']
+ reference_text = request.form.get('referenceText', '')
+
+ # 读取音频数据
+ audio_data = audio_file.read()
+
+ print(f"收到音频: {len(audio_data)} bytes")
+ print(f"参考文本: {reference_text}")
+
+ # 识别音频（百度API自动处理格式）
+ recognized_text, error = recognize_audio_baidu(audio_data, format='mp3')
+
+ if error:
+ return jsonify({
+ 'code': 500,
+ 'msg': f'识别失败: {error}'
+ }), 500
+
+ if not recognized_text:
+ return jsonify({
+ 'code': 500,
+ 'msg': '未识别到有效语音'
+ }), 500
+
+ # 计算评分
+ score = calculate_similarity(recognized_text, reference_text)
+ pronunciation_score = max(0, score - 5)
+ fluency_score = max(0, score - 3)
+
+ print(f"识别结果: {recognized_text}")
+ print(f"相似度: {score}分")
+
+ return jsonify({
+ 'code': 200,
+ 'msg': '成功',
+ 'data': {
+ 'recognizedText': recognized_text,
+ 'score': score,
+ 'pronunciationScore': pronunciation_score,
+ 'fluencyScore': fluency_score,
+ 'status': 'completed'
+ }
+ })
+
+ except Exception as e:
+ print(f"处理错误: {str(e)}")
+ return jsonify({
+ 'code': 500,
+ 'msg': f'处理失败: {str(e)}'
+ }), 500
+
+@app.route('/api/speech/health', methods=['GET'])
+def health():
+ """健康检查"""
+ client = get_asr_client()
+ return jsonify({
+ 'code': 200,
+ 'msg': '服务正常',
+ 'data': {
+ 'engine': 'baidu',
+ 'client_ready': client is not None
+ }
+ })
+
+if __name__ == '__main__':
+ print("=" * 50)
+ print("百度语音识别服务（超简单，无需ffmpeg）")
+ print("=" * 50)
+ print("")
+ print("1. 安装依赖: pip install baidu-aip")
+ print("2. 申请百度API: https://console.bce.baidu.com/ai/#/ai/speech/overview/index")
+ print("3. 填写 APP_ID, API_KEY, SECRET_KEY")
+ print("")
+
+ if BAIDU_APP_ID == "你的APP_ID":
+ print("⚠️ 请先配置百度API密钥！")
+ print("")
+
+ print("=" * 50)
+ print("服务启动成功！")
+ print("访问地址: http://localhost:5000")
+ print("=" * 50)
+ print("")
+
+ app.run(host='0.0.0.0', port=5000, debug=False)
diff --git a/fronted_uniapp/pages/speech/speech.vue b/fronted_uniapp/pages/speech/speech.vue
index cbc0019..10082c1 100644
--- a/fronted_uniapp/pages/speech/speech.vue
+++ b/fronted_uniapp/pages/speech/speech.vue
@@ -79,16 +79,6 @@
-
-
-