Daily Papers — 2026-09-27

1 papers on audio, speech, music, and acoustics.

1. From Script to Drama: An Agentic Framework for Controllable Multi-Speaker Dialogue TTS

Authors: Kangxiang Xia, Xinfa Zhu, HangRui Hu, Kexin Huang, Wenjie Tian et al.

Categories: eess.AS, cs.CL, cs.SD Score: 4.11/10 (Obj:7 Id:4 Ind:2 Comp:4 Eff:5 Nov:4 Rep:2)

• Strength: 同一 backbone 下把「重合成」换成「编辑」，Gemini 判定的 Yes 率从 87.0% 升到 95.5%，人工测试对 utterance-only 消融 73 胜 6 负。
• Weakness: critique 与评委是同一个 Gemini 模型，且缺少 Step-Audio-EditX 这一直接对位的开源编辑模型，外部基线的差距无法与「对评委做拒绝采样」区分开。
• Full review: Claude Code 全文七公理审稿

Multi-speaker dialogue TTS requires natural speech generation, consistent speaker identity, coherent cross-turn transitions, and fine-grained control of expressive attributes such as emotion, speaking rate, and loudness. These requirements are difficult to satisfy reliably with one-shot generation, especially in long-form dialogue. We propose a controllable multi-speaker dialogue TTS framework that formulates synthesis as critique-driven iterative refinement. Its speech backbone, ControlEdit-TTS, unifies instruction-following synthesis and natural-language-guided attribute editing, enabling correction of expressive errors without full regeneration. The framework further performs hierarchical utterance-level and scene-level critique, routing detected issues to editing, resynthesis, or timing adjustment. Experiments on a bilingual Chinese–English dialogue benchmark show improved utterance-level instruction following, better dialogue-level preference than direct dialogue models and agentic baselines, and more effective refinement than regeneration-only alternatives while preserving speaker identity. Ablations further confirm the benefits of scene-level critique and edit-based correction.