LocalVQE v1.4-AEC

此 Soniqo 页面记录本地 speech-swift 实现中的 LocalVQE v1.4-AEC。Hugging Face 包链接放在集成说明之后。

先进入站内页面

首页卡片和文档菜单先指向这里；源模型和权重包链接仍在本页提供。

概览

模型	LocalVQE v1.4-AEC
用途	Explicit-reference acoustic echo cancellation
后端	Native C++ adaptive filter plus stateful Core ML residual mask
输出	16 kHz mono Float32 clean-microphone PCM
语言	Language-independent acoustic processing
许可证	Apache-2.0 code and weights
状态	Streaming and complete-clip speech-swift runtime
来源	LocalVQE
Swift 产品	`SpeechEnhancement`
CLI / 运行时	Programmatic LocalVQEEchoCanceller runtime

使用

下面的片段对应当前 speech-swift 仓库暴露的 API 或命令。

import SpeechEnhancement

let aec = try await LocalVQEEchoCanceller.fromPretrained()
let cleanMicrophone = try aec.processFrame(
    microphone: microphoneFrame,
    reference: playbackReferenceFrame
)

模型链接

实现说明

Microphone and playback reference are separate, synchronized inputs; a mixed system-audio transcript is not a valid reference.
Streaming accepts exactly 256 mono samples per input at 16 kHz and adds one 16 ms spectral hop of algorithmic latency.
Reset after dropped frames, device changes, capture restarts, or recording boundaries so stale filter and neural state cannot cross discontinuities.
A silent reference preserves microphone-only speech; the runtime never falls back to subtracting a mix or muting the microphone.
Do not blindly cascade this path with Apple Voice Processing I/O because two adaptive cancellers can distort near-end speech.