#artificial intelligence
May 2026
Liberating LLM Capabilities in Full-Duplex Speech Models
Listen-Write-Speak (LWS), a text-first tri-channel paradigm in which a single autoregressive LLM continuously listens to user audio, writes visible free-form text as its primary output, and speaks a realtime oral response in parallel under a shared causal attention context is proposed.
Luo-Yuan Zhang, Bo-Kai Xu, Jun-Bo Cui et al.
· arXiv.org · 1 citation