2 papers
cs.CL2026
Same Words, Different Actions: Paired Turn-Taking Evaluation under Rewritten Dialogue Contexts
Shuofeng Zhao, Hongwei Cai, Wenke Fan +9
Real-time spoken dialogue systems must distinguish interruptions that require yielding the floor from backchannels that permit continued speaking. Existing benchmarks typically sco…
cs.CL2026
Poly-InstructTTS: Learning In-the-Wild Expressive Speech Synthesis from Open-Ended Instructions
Junhui Zhang, Qianhui Xu, Qingxiang Guo +4
While recent text-to-speech (TTS) models achieve high naturalness, controlling fine-grained expression via natural-language instructions remains challenging. We introduce Poly- Ins…