WebRTC author Justin Uberti: diarization is the wrong path, train LLMs on noise
juberti · x · 2026-10-14
Justin Uberti argues speaker diarization is the wrong direction for voice AI — effort spent producing human-legible features when the right fix is training LLMs to handle background noise directly ("bitter lesson strikes again"). He adds background voice cancellation helps but is underparameterized: if a human might struggle with an audio task, a small model has no chance.
More from Models
- Arcee teases another model release tomorrow right after shipping its 24B — JosephJacks_ · 2026-10-14
- OpenRouter decision model market share: TypeSafe commands 82.8% — nischay_twt · 2026-10-14
- Anthropic's rumored Fable 5.5 model didn't ship this week as expected — imjustnewatai · 2026-10-14
- One prompt, three personalities: GPT, Gemini and Opus trade sparkling jokes — emollick · 2026-10-14
- Gemini Argon's table preference plunges to 31.5% from Flash's 85.9% in new test — dejanseo · 2026-10-14
- User blasts Claude for refusing to click a Terms & Conditions button — Angaisb_ · 2026-10-14