task · first seen 23 Oct 2026
streaming speech recognition and synthesis
Real-time speech-to-text and text-to-speech processing that handles input and output incrementally.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Uni-Stream: A Unified Streaming Speech Language Model for Speech Synthesis and RecognitionPapers · 23 Oct 2026 · Xuan Shi, Chang Zeng, Tiantian Feng, Ye Zhang, Jun Liu, Shih-Heng Wang, Lie Lu,…
Latest sources
- Uni-Stream: A Unified Streaming Speech Language Model for Speech Synthesis and RecognitionPapers · 23 Oct 2026 · Xuan Shi, Chang Zeng, Tiantian Feng, Ye Zhang, Jun Liu, Shih-Heng Wang, Lie Lu,…