Sesame Releases TurnBench for Real-Time Conversational Turn-Taking
shinjiw_at_cmu · x · 2026-08-29
Sesame released TurnBench, a multi-domain benchmark for evaluating "when to speak and when to yield" in real-time conversations. It features a 30-hour dual-channel corpus with hand-annotated end-of-turn and interruption events. The leaderboard ranks models by recall, FPR, and latency; Voice Activity Projection leads with 0.845 recall, while OpenAI Realtime (Semantic VAD) scores 0.303. The training set, otoSpeech, is available on Hugging Face.
Related event: Sesame Releases TurnBench for Evaluating Voice AI Turn-Taking(2 posts)→
More from Research
- Learn Positional Encodings derivation from first principles — zainhas · 2026-08-30
- COLM Paper Traces Capability Provenance in LLMs via Gradient Attribution — ziv_ravid · 2026-08-30
- Toby Ord paper argues recursive self-improvement has physical limits — Exponential View (Azeem Azhar) · 2026-08-30
- AI Formalization Tools Fable and Sol Spot First Repairable Error in Published Literature — Sauers_ · 2026-08-30
- Mark Schmidt Posts ICML Tutorial Video: Is Numerical Optimization Theory Irrelevant to ML Practice in 2026? — MarkSchmidtUBC · 2026-08-30
- SDF Donut in 46 Lines of Python — voooooogel · 2026-08-30