MMEDIT: A Unified Framework for Multi-Type Audio Editing via Audio Language Model

TL;DR

MMEdit introduces a comprehensive, scalable framework for multi-type audio editing that leverages audio-language models to improve localization, instruction adherence, and fidelity across diverse editing operations.

Contribution

It extends audio editing task definitions, develops a large-scale paired dataset, and integrates advanced cross-modal models for precise, flexible audio modifications.

Findings

Achieves superior localization accuracy in editing tasks

Demonstrates robust adherence to editing instructions

Maintains high fidelity in non-edited audio regions

Abstract

Text-guided audio editing aims to modify specific acoustic events while strictly preserving non-target content. Despite recent progress, existing approaches remain fundamentally limited. Training-free methods often suffer from signal degradation caused by diffusion inversion, while training-based methods, although achieving higher generation quality, are severely constrained by the scarcity of high-quality paired data and task formulations that cover only a narrow subset of editing operations. In addition, standard architectures typically decouple text and audio processing, limiting the ability to align instructions with specific acoustic contexts. To address these challenges, we propose MMEdit, an audio-language-model-driven framework for unified audio editing. We systematically extend task definitions to cover a comprehensive range of editing operations, including addition, replacement, removal, reordering, and attribute modification. Furthermore, we design a scalable data synthesis pipeline to construct large-scale paired datasets with fine-grained event-level annotations. To capture complex editing semantics, we integrate a Qwen2-Audio encoder with an MMDiT-based generator, enabling precise cross-modal alignment and localized editing. Experimental results demonstrate that our method achieves superior editing localization accuracy, robust instruction following, and high fidelity in non-edited regions.