lotus(#1): ML denoise as a first-class audio TrackProcessor (fixes A7)
Implements RNNoise/Speex noise suppression as a LiveKit audio TrackProcessor attached to the local mic track, replacing the host's build-time getUserMedia monkeypatch. Because EC re-attaches the processor on every (re)publish (LocalTrackPublished), denoise now survives EC's mid-call reconnect — the root cause of A7 "mic dead after reconnect". Reuses the worklet/wasm assets already shipped under ./denoise/ (no new EC dependency); model/gate configured via lotusDenoise/lotusModel/lotusGate URL params. Additive: no-op unless lotusDenoise=ml. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 4.8
parent
33d0e98eb0
commit
39b57db3b2
@@ -0,0 +1,98 @@
|
||||
/*
|
||||
Copyright 2026 Lotus Guild
|
||||
|
||||
SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-Element-Commercial
|
||||
Please see LICENSE in the repository root for full details.
|
||||
*/
|
||||
|
||||
import {
|
||||
type LocalAudioTrack,
|
||||
ParticipantEvent,
|
||||
type Room as LivekitRoom,
|
||||
Track,
|
||||
} from "livekit-client";
|
||||
import { logger } from "matrix-js-sdk/lib/logger";
|
||||
|
||||
import { type CallViewModel } from "../state/CallViewModel/CallViewModel";
|
||||
import { lotusFlag, lotusParam } from "./lotusWidget";
|
||||
import {
|
||||
type LotusDenoiseConfig,
|
||||
LotusDenoiseProcessor,
|
||||
} from "./lotusDenoiseProcessor";
|
||||
|
||||
/**
|
||||
* Apply Lotus ML noise suppression to the local mic track as a first-class
|
||||
* Element Call audio TrackProcessor (#1), replacing the host's build-time
|
||||
* `getUserMedia` monkeypatch.
|
||||
*
|
||||
* Opt-in via `lotusDenoise=ml` (+ `lotusModel`, `lotusGate`,
|
||||
* `lotusGateThreshold`, `lotusDenoiseBase`). Because the processor is attached
|
||||
* to the mic publication and re-attached on every (re)publish, denoise
|
||||
* survives EC's mid-call reconnect — fixing the A7 "mic dead after reconnect"
|
||||
* bug. Additive: no-op without the flag.
|
||||
*/
|
||||
export function startLotusDenoise(vm: CallViewModel): () => void {
|
||||
if (lotusParam("lotusDenoise") !== "ml") return () => undefined;
|
||||
|
||||
const config: LotusDenoiseConfig = {
|
||||
model: lotusParam("lotusModel") === "speex" ? "speex" : "rnnoise",
|
||||
assetBase: lotusParam("lotusDenoiseBase") || "./denoise/",
|
||||
gate: lotusFlag("lotusGate"),
|
||||
gateThreshold: Number(lotusParam("lotusGateThreshold")) || -50,
|
||||
};
|
||||
|
||||
const micOf = (room: LivekitRoom): LocalAudioTrack | undefined =>
|
||||
room.localParticipant.getTrackPublication(Track.Source.Microphone)
|
||||
?.track as LocalAudioTrack | undefined;
|
||||
|
||||
const apply = (room: LivekitRoom): void => {
|
||||
const mic = micOf(room);
|
||||
if (mic && !mic.getProcessor()) {
|
||||
void mic
|
||||
.setProcessor(new LotusDenoiseProcessor(config))
|
||||
.catch((e) => logger.warn("[lotus] denoise setProcessor failed", e));
|
||||
}
|
||||
};
|
||||
|
||||
const roomListeners = new Map<LivekitRoom, () => void>();
|
||||
let rooms: LivekitRoom[] = [];
|
||||
|
||||
const sub = vm.livekitRoomItems$.subscribe((items) => {
|
||||
const next = items.map((i) => i.livekitRoom);
|
||||
rooms = next;
|
||||
for (const [room, off] of roomListeners) {
|
||||
if (!next.includes(room)) {
|
||||
off();
|
||||
roomListeners.delete(room);
|
||||
}
|
||||
}
|
||||
for (const room of next) {
|
||||
if (!roomListeners.has(room)) {
|
||||
// Re-attach on every (re)publish — this is what makes denoise survive
|
||||
// reconnects (A7), unlike the old getUserMedia patch.
|
||||
const onPublished = (): void => apply(room);
|
||||
room.localParticipant.on(
|
||||
ParticipantEvent.LocalTrackPublished,
|
||||
onPublished,
|
||||
);
|
||||
roomListeners.set(room, () =>
|
||||
room.localParticipant.off(
|
||||
ParticipantEvent.LocalTrackPublished,
|
||||
onPublished,
|
||||
),
|
||||
);
|
||||
apply(room);
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
return () => {
|
||||
sub.unsubscribe();
|
||||
for (const off of roomListeners.values()) off();
|
||||
roomListeners.clear();
|
||||
for (const room of rooms) {
|
||||
const mic = micOf(room);
|
||||
if (mic?.getProcessor()) void mic.stopProcessor();
|
||||
}
|
||||
};
|
||||
}
|
||||
@@ -0,0 +1,151 @@
|
||||
/*
|
||||
Copyright 2026 Lotus Guild
|
||||
|
||||
SPDX-License-Identifier: AGPL-3.0-only OR LicenseRef-Element-Commercial
|
||||
Please see LICENSE in the repository root for full details.
|
||||
*/
|
||||
|
||||
import {
|
||||
type AudioProcessorOptions,
|
||||
type Track,
|
||||
type TrackProcessor,
|
||||
} from "livekit-client";
|
||||
import { logger } from "matrix-js-sdk/lib/logger";
|
||||
|
||||
export type LotusDenoiseModel = "rnnoise" | "speex";
|
||||
|
||||
export interface LotusDenoiseConfig {
|
||||
model: LotusDenoiseModel;
|
||||
/** Base URL the worklet scripts + wasm are served from (e.g. "./denoise/"). */
|
||||
assetBase: string;
|
||||
gate: boolean;
|
||||
gateThreshold: number;
|
||||
}
|
||||
|
||||
// Flat sapphi worklets: each registers a processor under these names when its
|
||||
// script module is added. Same assets the Lotus host already ships under
|
||||
// public/element-call/denoise/, so no new EC dependency is needed.
|
||||
const PROCESSORS: Record<
|
||||
LotusDenoiseModel,
|
||||
{ name: string; script: string; wasm: string }
|
||||
> = {
|
||||
rnnoise: {
|
||||
name: "@sapphi-red/web-noise-suppressor/rnnoise",
|
||||
script: "rnnoiseWorklet.js",
|
||||
wasm: "rnnoise.wasm",
|
||||
},
|
||||
speex: {
|
||||
name: "@sapphi-red/web-noise-suppressor/speex",
|
||||
script: "speexWorklet.js",
|
||||
wasm: "speex.wasm",
|
||||
},
|
||||
};
|
||||
const GATE_NAME = "@sapphi-red/web-noise-suppressor/noiseGate";
|
||||
const GATE_SCRIPT = "noiseGateWorklet.js";
|
||||
|
||||
/**
|
||||
* A LiveKit audio TrackProcessor that runs Lotus ML noise suppression
|
||||
* (RNNoise/Speex) on the local microphone track, as a first-class stage in
|
||||
* Element Call's publish pipeline.
|
||||
*
|
||||
* This replaces the host's `getUserMedia` monkeypatch: because it's a real
|
||||
* LiveKit processor, EC re-applies it on every (re)publish, so denoise
|
||||
* survives EC's own mid-call reconnect — the root cause of the A7
|
||||
* "mic dead after reconnect" bug.
|
||||
*/
|
||||
export class LotusDenoiseProcessor
|
||||
implements TrackProcessor<Track.Kind.Audio, AudioProcessorOptions>
|
||||
{
|
||||
public readonly name = "lotus-denoise";
|
||||
public processedTrack?: MediaStreamTrack;
|
||||
|
||||
private source?: MediaStreamAudioSourceNode;
|
||||
private nodes: AudioWorkletNode[] = [];
|
||||
|
||||
public constructor(private readonly config: LotusDenoiseConfig) {}
|
||||
|
||||
public async init(opts: AudioProcessorOptions): Promise<void> {
|
||||
await this.build(opts.audioContext, opts.track);
|
||||
}
|
||||
|
||||
public async restart(opts: AudioProcessorOptions): Promise<void> {
|
||||
this.teardownGraph();
|
||||
await this.build(opts.audioContext, opts.track);
|
||||
}
|
||||
|
||||
public async destroy(): Promise<void> {
|
||||
this.teardownGraph();
|
||||
}
|
||||
|
||||
private async build(
|
||||
ctx: AudioContext,
|
||||
track: MediaStreamTrack,
|
||||
): Promise<void> {
|
||||
const base = this.config.assetBase;
|
||||
const proc = PROCESSORS[this.config.model];
|
||||
|
||||
// Register worklet modules (idempotent) and load the wasm binary.
|
||||
await ctx.audioWorklet.addModule(base + proc.script);
|
||||
if (this.config.gate) await ctx.audioWorklet.addModule(base + GATE_SCRIPT);
|
||||
const wasmBinary = await fetch(base + proc.wasm).then((r) => {
|
||||
if (!r.ok) throw new Error(`denoise wasm ${r.status}`);
|
||||
return r.arrayBuffer();
|
||||
});
|
||||
|
||||
const source = ctx.createMediaStreamSource(new MediaStream([track]));
|
||||
const dest = ctx.createMediaStreamDestination();
|
||||
let head: AudioNode = source;
|
||||
|
||||
if (this.config.gate) {
|
||||
const gate = new AudioWorkletNode(ctx, GATE_NAME, {
|
||||
processorOptions: {
|
||||
openThreshold: this.config.gateThreshold,
|
||||
closeThreshold: this.config.gateThreshold - 5,
|
||||
holdMs: 150,
|
||||
maxChannels: 1,
|
||||
},
|
||||
});
|
||||
head.connect(gate);
|
||||
head = gate;
|
||||
this.nodes.push(gate);
|
||||
}
|
||||
|
||||
const ml = new AudioWorkletNode(ctx, proc.name, {
|
||||
channelCount: 1,
|
||||
numberOfInputs: 1,
|
||||
numberOfOutputs: 1,
|
||||
processorOptions: { maxChannels: 1, wasmBinary },
|
||||
});
|
||||
head.connect(ml);
|
||||
ml.connect(dest);
|
||||
this.nodes.push(ml);
|
||||
|
||||
this.source = source;
|
||||
this.processedTrack = dest.stream.getAudioTracks()[0];
|
||||
logger.info(`[lotus] denoise processor active (${this.config.model})`);
|
||||
}
|
||||
|
||||
private teardownGraph(): void {
|
||||
for (const node of this.nodes) {
|
||||
try {
|
||||
node.port.postMessage("destroy");
|
||||
} catch {
|
||||
/* ignore */
|
||||
}
|
||||
try {
|
||||
node.disconnect();
|
||||
} catch {
|
||||
/* ignore */
|
||||
}
|
||||
}
|
||||
this.nodes = [];
|
||||
try {
|
||||
this.source?.disconnect();
|
||||
} catch {
|
||||
/* ignore */
|
||||
}
|
||||
this.source = undefined;
|
||||
this.processedTrack?.stop();
|
||||
this.processedTrack = undefined;
|
||||
}
|
||||
}
|
||||
@@ -34,6 +34,7 @@ import { startLotusFocus } from "../lotus/lotusFocus";
|
||||
import { startLotusAudioInject } from "../lotus/lotusAudioInject";
|
||||
import { startLotusQuality } from "../lotus/lotusQuality";
|
||||
import { startLotusDecorations } from "../lotus/lotusDecorations";
|
||||
import { startLotusDenoise } from "../lotus/lotusDenoise";
|
||||
import styles from "./InCallView.module.css";
|
||||
import { GridTile } from "../tile/GridTile";
|
||||
import { SettingsModal, defaultSettingsTab } from "../settings/SettingsModal";
|
||||
@@ -299,6 +300,9 @@ export const InCallView: FC<InCallViewProps> = ({
|
||||
// [lotus] Receive per-user avatar-decoration URLs from the host and render
|
||||
// them on in-call tile avatars (#6). No-op unless the host sends them.
|
||||
useEffect(() => startLotusDecorations(), []);
|
||||
// [lotus] Apply ML denoise to the mic as a first-class audio processor that
|
||||
// survives reconnects (#1 / A7). No-op unless lotusDenoise=ml.
|
||||
useEffect(() => startLotusDenoise(vm), [vm]);
|
||||
|
||||
const fatalCallError = useBehavior(vm.fatalError$);
|
||||
// Stop the rendering and throw for the error boundary
|
||||
|
||||
Reference in New Issue
Block a user