[本地语音降噪]：完成本地语音链路和噪音过滤，包含降噪模型、本地ASR和实时字幕稳定策略

src/owner_voice_pet/assistant_pipeline.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 from dataclasses import dataclass, field
 from typing import Protocol
 
+from .audio_preprocess import NoopAudioPreprocessor
 from .config import AppConfig
 from .conversation import ConversationContext
 from .events import (
@@ -28,6 +29,7 @@ from .events import (
 )
 from .models import AudioFrame, AudioSegment, ErrorCode, PipelineState, ProviderError
 from .protocols import (
+    AudioPreprocessor,
     AudioTransport,
     LlmProvider,
     RealtimeSttProvider,
@@ -77,6 +79,7 @@ class TurnController:
         transport: AudioTransport,
         wakeword: WakeWordProvider,
         vad_recorder: VadRecorder,
+        audio_preprocessor: AudioPreprocessor,
         stt: SttProvider,
         realtime_stt: RealtimeSttProvider | None,
         llm: LlmProvider,
@@ -90,6 +93,7 @@ class TurnController:
         self.transport = transport
         self.wakeword = wakeword
         self.vad_recorder = vad_recorder
+        self.audio_preprocessor = audio_preprocessor
         self.stt = stt
         self.realtime_stt = realtime_stt
         self.llm = llm
@@ -157,6 +161,7 @@ class TurnController:
     def _capture_segment(self, turn_id: int, *, state_message: str) -> AudioSegment | ProviderError:
         self.vad_recorder.reset()
         self.vad_recorder.provider.reset()
+        self.audio_preprocessor.reset()
         realtime_session = self._start_realtime_transcript()
         self._event(CAPTURE_STARTED, PipelineState.RECORDING, state_message, turn_id=turn_id)
         while True:
@@ -164,6 +169,10 @@ class TurnController:
             if not frames:
                 continue
             for frame in frames:
+                try:
+                    frame = self.audio_preprocessor.process_frame(frame)
+                except ProviderError as exc:
+                    return exc
                 was_started = self.vad_recorder.started
                 result = self.vad_recorder.feed(frame)
                 if not was_started and self.vad_recorder.started:
@@ -310,6 +319,7 @@ class VoiceAssistantPipeline:
         llm: LlmProvider,
         tts: TtsProvider,
         context: ConversationContext,
+        audio_preprocessor: AudioPreprocessor | None = None,
         realtime_stt: RealtimeSttProvider | None = None,
         ack_tts: TtsProvider | None = None,
         reporter: RuntimeReporter | None = None,
@@ -320,6 +330,7 @@ class VoiceAssistantPipeline:
         self.transport = transport
         self.wakeword = wakeword
         self.vad_recorder = vad_recorder
+        self.audio_preprocessor = audio_preprocessor or NoopAudioPreprocessor()
         self.stt = stt
         self.realtime_stt = realtime_stt
         self.llm = llm
@@ -336,6 +347,7 @@ class VoiceAssistantPipeline:
             transport=transport,
             wakeword=wakeword,
             vad_recorder=vad_recorder,
+            audio_preprocessor=self.audio_preprocessor,
             stt=stt,
             realtime_stt=realtime_stt,
             llm=llm,
@@ -349,6 +361,7 @@ class VoiceAssistantPipeline:
     def load(self) -> None:
         self.wakeword.load()
         self.vad_recorder.provider.load()
+        self.audio_preprocessor.load()
         self.stt.load()
         if self.realtime_stt is not None and self.realtime_stt is not self.stt:
             self.realtime_stt.load()