arXiv cs.AI· Hankun Wang, Bohan Li, Shi Lian, Xiaoyu Gu, Jing Peng, Da Zheng, Yiwei Guo, Colin Zhang, Shuai Wang, Kai Yu·· 14 小时前AI 评分35
dots.tts.edit：基于连续自回归模型的精准可控语音编辑
dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model
AI 导读
dots.tts.edit 是一个基于连续自回归语音生成架构的语音编辑模型，采用半形式化的转写文本指令，将操作类别与参数绑定到转写片段或边界，无需显式时间戳对齐。
正文 · 原文
Abstract:Speech editing for content creation requires precise control over both what an edit should do and where it should apply. Free-form natural language provides a flexible interface for expressing edit requests, but its ambiguity may leave the intended operation, parameters, or target region underspecified. We study a semi-formal transcript-grounded edit instruction that specifies operation categories and parameters and binds them to transcript spans or boundaries. This semantic timeline avoids explicit timestamp alignment and provides an externally inspectable contract for compositional edits. We instantiate the interface in dots$.$tts$.$edit, a speech editing model built on a continuous autoregressive speech generation architecture. Four representative speech-creation controls cover lexical content, affective expression, pitch and speaking-rate delivery, and temporal phrasing through text, emotion, prosody, and pause editing. Task-specific data pipelines construct operation- and scope-controlled pairs while retaining source-derived context outside each target region. We further introduce doteBench, a bilingual benchmark that measures precise instruction following, local preservation, and audio quality across the four controls and their composition. Experiments show leading overall instruction following and local preservation across its five editing categories, while audio quality remains comparable to existing open-source systems. Across three Seed-TTS-Eval shards, the model shows negligible differences from the base model in zero-shot TTS recognition error rate and speaker similarity.
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Audio and Speech Processing (eess.AS) |
| Cite as: | arXiv:2608.02673 [cs.SD] |
| (or arXiv:2608.02673v4 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2608.02673 arXiv-issued DOI via DataCite |
Submission history
From: Hankun Wang [view email]
[v1]
Sun, 2 Aug 2026 15:03:37 UTC (319 KB)
[v2]
Tue, 11 Aug 2026 17:29:29 UTC (323 KB)
[v3]
Mon, 28 Sep 2026 12:47:03 UTC (353 KB)
[v4]
Wed, 28 Oct 2026 18:58:32 UTC (1,231 KB)
来源：arXiv cs.AI · arxiv.org