Files

Juergen Kunz f3e1c96872 initial commit — SIP B2BUA + WebRTC bridge with Rust codec engine

Full-featured SIP router with multi-provider trunking, browser softphone
via WebRTC, real-time Opus/G.722/PCM transcoding in Rust, RNNoise ML
noise suppression, Kokoro neural TTS announcements, and a Lit-based
web dashboard with live call monitoring and REST API.

2026-04-09 23:03:55 +00:00

1.0 KiB

Raw Permalink Blame History

Ideas / Future Improvements

nnnoiseless (RNNoise) Denoiser Improvements

VAD-gated passthrough

process_frame() returns an f32 VAD probability (0.0-1.0). Currently ignored. Use it to skip denoising when VAD is low — prevents the model from suppressing non-speech audio (hold music, DTMF tones, IVR prompts).

Pre-warm denoiser on session creation

The first process_frame() call on a fresh DenoiseState produces fade-in artifacts (documented behavior). Feed a silent 480-sample frame during TranscodeState::new() so the first real audio frame gets a warmed-up RNN state.

Custom telephony-trained RNNoise model

nnnoiseless supports loading custom .rnn model files via RnnModel::from_bytes() / RnnModel::from_static_bytes(). The default model is trained on general audio. A model trained specifically on telephony noise profiles (codec artifacts, line noise, echo residual) would perform better. Models from https://github.com/GregorR/rnnoise-models can be converted with train/convert_rnnoise.py.