Coupled but Late: Turn-Taking Between Full-Duplex Speech Models in Unscripted Dialogue
Full-duplex speech models are trained to converse with a person, but they are increasingly made to converse with each other, in self-play data generation, agent societies, and model-based evaluation.
ProofPaper ↗
Key points
- In that loop no human absorbs a timing error: each model's turn-taking is the other's input.
- We ask what timing the loop settles into.
- Two PersonaPlex-7B instances exchange audio tokens on a shared clock in unscripted conversation, and one floor-transfer rule is applied to them and to Switchboard.
- Their timing is coupled: re-pairing speakers across conversations destroys it.
Sources (1)
- [1]Coupled but Late: Turn-Taking Between Full-Duplex Speech Models in Unscripted DialoguearXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 05:03 PM
Full-duplex speech models are trained to converse with a person, but they are increasingly made to converse with each other, in self-play data generation, agent societies, and model-based evaluation.
In that loop no human absorbs a timing error: each model's turn-taking is the other's input.
Extractive summary: sentences quoted from the sources.