CoSTA compresses speech tokens for faster spoken dialogue models
On bilingual benchmarks, generation speed rises about 1.7 times while response quality is preserved.
Stories per day · 30 days
2 RSS
4 stories, newest first · one card per story
Stories tagged #spoken-dialogue
Conversation Is a Two-Body Problem: Dyadic Evaluation of Full-Duplex Dialogue Models
DyaFDB scores both sides of 7,560 full-duplex model conversations instead of using a fixed examiner.
Realtime-Venus: A full-duplex interaction system with asynchronous delegation
Realtime-Venus introduces two 9B full-duplex interaction models (Omni and Audio) that outperform Gemini 3.1 Live and GPT-4o on continuation metrics.
Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue
Researchers introduce Motion-Omni, an end-to-end model generating speech with synchronized full-body motion, responding 5.4x faster than cascade pipelines.