update: 增加唤醒时声纹处理 ，1秒内发送至大模型 【需优化唤醒锁机制，中途会遭受打断(偶发)，考虑忽略检测】

main/xiaozhi-server/core/handle/receiveAudioHandle.py

@@ -1,26 +1,21 @@
 import time
 import json
-import asyncio
-from core.utils.util import audio_to_data_stream
 from core.handle.abortHandle import handleAbortMessage
 from core.handle.intentHandler import handle_user_intent
 from core.utils.output_counter import check_device_output_limit
+from core.utils.util import play_audio_frames, play_audio_response
 from core.handle.sendAudioHandle import send_stt_message, SentenceType
 
 TAG = __name__
 
 
 async def handleAudioMessage(conn, audio):
+    # 检查是否在唤醒处理锁定期内
+    if getattr(conn, 'wakeup_processing_lock', 0) > time.monotonic():
+        return
+    
     # 当前片段是否有人说话
     have_voice = conn.vad.is_vad(conn, audio)
-    # 如果设备刚刚被唤醒，短暂忽略VAD检测
-    if have_voice and hasattr(conn, "just_woken_up") and conn.just_woken_up:
-        have_voice = False
-        # 设置一个短暂延迟后恢复VAD检测
-        conn.asr_audio.clear()
-        if not hasattr(conn, "vad_resume_task") or conn.vad_resume_task.done():
-            conn.vad_resume_task = asyncio.create_task(resume_vad_detection(conn))
-        return
     if have_voice:
         if conn.client_is_speaking:
             await handleAbortMessage(conn)
@@ -29,13 +24,6 @@ async def handleAudioMessage(conn, audio):
     # 接收音频
     await conn.asr.receive_audio(conn, audio, have_voice)
 
-
-async def resume_vad_detection(conn):
-    # 等待2秒后恢复VAD检测
-    await asyncio.sleep(1)
-    conn.just_woken_up = False
-
-
 async def startToChat(conn, text):
     # 检查输入是否是JSON格式（包含说话人信息）
     speaker_name = None
@@ -119,9 +107,7 @@ async def max_out_size(conn):
     text = "不好意思，我现在有点事情要忙，明天这个时候我们再聊，约好了哦！明天不见不散，拜拜！"
     await send_stt_message(conn, text)
     file_path = "config/assets/max_output_size.wav"
-    conn.tts.tts_audio_queue.put((SentenceType.FIRST, [], text))
-    play_audio_frames(conn, file_path)
-    conn.tts.tts_audio_queue.put((SentenceType.LAST, [], None))
+    play_audio_response(conn, {"text": text, "file_path": file_path})
     conn.close_after_chat = True
 
 
@@ -156,17 +142,4 @@ async def check_bind_device(conn):
         text = f"没有找到该设备的版本信息，请正确配置 OTA地址，然后重新编译固件。"
         await send_stt_message(conn, text)
         music_path = "config/assets/bind_not_found.wav"
-        conn.tts.tts_audio_queue.put((SentenceType.FIRST, [], text))
-        play_audio_frames(conn, music_path)
-        conn.tts.tts_audio_queue.put((SentenceType.LAST, [], None))
-
-def play_audio_frames(conn, file_path):
-    """播放音频文件并处理发送帧数据"""
-    def handle_audio_frame(frame_data):
-        conn.tts.tts_audio_queue.put((SentenceType.MIDDLE, frame_data, None))
-
-    audio_to_data_stream(
-        file_path,
-        is_opus=True,
-        callback=handle_audio_frame
-    )
+        play_audio_response(conn, {"text": text, "file_path": music_path})