[2601.21463] Unifying Speech Editing Detection and Content Localization via Prior-Enhanced Audio LLMs

Computer Science > Sound arXiv:2601.21463 (cs) [Submitted on 29 Jan 2026 (v1), last revised 8 Apr 2026 (this version, v2)] Title:Unifying Speech Editing Detection and Content Localization via Prior-Enhanced Audio LLMs Authors:Jun Xue, Yi Chai, Yanzhen Ren, Jinshen He, Zhiqiang Tang, Zhuolin Yi, Yihuan Huang, Yuankun Xie, Yujie Chen View a PDF of the paper titled Unifying Speech Editing Detection and Content Localization via Prior-Enhanced Audio LLMs, by Jun Xue and 8 other authors View PDF HTML (experimental) Abstract:Existing speech editing detection (SED) datasets are predominantly constructed using manual splicing or limited editing operations, resulting in restricted diversity and poor coverage of realistic editing scenarios. Meanwhile, current SED methods rely heavily on frame-level supervision to detect observable acoustic anomalies, which fundamentally limits their ability to handle deletion-type edits, where the manipulated content is entirely absent from the signal. To address these challenges, we present a unified framework that bridges speech editing detection and content localization through a generative formulation based on Audio Large Language Models (Audio LLMs). We first introduce AiEdit, a large-scale bilingual dataset (approximately 140 hours) that covers addition, deletion, and modification operations using state-of-the-art end-to-end speech editing systems, providing a more realistic benchmark for modern threats. Building upon this, we reformulate SED a...