Preprint
Sep 2026
What Did I Just Say? Self-Listening for Full-Duplex Speech Models
Self-Listening is proposed, a full-duplex modeling approach that interleaves user speech, model text, and the model's played speech so that interruption recovery in what the user has actually heard is grounds in what the user has actually heard.
Xuan-Ning Zhou, Junyi Ao, Xiao-Tong Liu et al.
· 0 citations