task · first seen 15 Oct 2026
streaming audio-visual speech generation
Generating synchronized speech and facial video in real time as a conversational agent responds.
Mentions per week
PapersCodeDiscussion
Earliest sources
- JAVIS: Joint Audio-Visual Interaction and Streaming for Real-Time Conversational AgentsPapers · 15 Oct 2026 · Junseok Ahn, Jaehyun Park, Jeongsoo Choi, Joon Son Chung, Ji-Hoon Kim
Latest sources
- JAVIS: Joint Audio-Visual Interaction and Streaming for Real-Time Conversational AgentsPapers · 15 Oct 2026 · Junseok Ahn, Jaehyun Park, Jeongsoo Choi, Joon Son Chung, Ji-Hoon Kim