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

TL;DR

This paper introduces a unified speech editing detection and content localization framework using Audio LLMs, supported by a new realistic dataset and innovative prompting and loss strategies.

Contribution

It presents AiEdit, a comprehensive bilingual dataset, and reformulates SED as a structured text generation task with prior-enhanced prompting and acoustic consistency loss.

Findings

Outperforms existing methods in detection accuracy.

Effectively handles addition, deletion, and modification edits.

Improves joint reasoning over edit type and content localization.

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 as a structured text generation task, enabling joint reasoning over edit type identification, and content localization. To enhance the grounding of generative models in acoustic evidence, we propose a prior-enhanced prompting strategy that injects word-level probabilistic cues derived from a frame-level detector. Furthermore, we introduce an acoustic consistency-aware loss that explicitly enforces the separation between normal and anomalous acoustic representations in the latent space. Experimental results demonstrate that the proposed approach consistently outperforms existing methods across both detection and localization tasks.