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

arXiv: https://arxiv.org/abs/2512.20339 · HTML: https://mlsanity.com/paper/2512.20339/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2025.

## Built on by (most cited first, 9 of 9)

- [Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing](https://mlsanity.com/paper/2604.10708/) (2026)
- [MMAE: A Massive Multitask Audio Editing Benchmark](https://mlsanity.com/paper/2606.07229/) (2026)
- [UNISON: A Unified Sound Generation and Editing Framework via Deep LLM Fusion](https://mlsanity.com/paper/2605.31530/) (2026)
- [FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing](https://mlsanity.com/paper/2606.15186/) (2026)
- [AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing](https://mlsanity.com/paper/2609.08936/) (2026)
- [RFM-Editing 2: Text-Guided Audio Editing with Rectified Flow Matching and Coarse-to-Fine Diffusion Transformers](https://mlsanity.com/paper/2606.20101/) (2026)
- [TORUS: A Test of Rendering-Understanding Self-Coherence for Unified Audio Models](https://mlsanity.com/paper/2607.28896/) (2026)
- [dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model](https://mlsanity.com/paper/2608.02673/) (2026)
- [TV-AudioRemover: Joint Text-Visual Guided Sound Removal with Multi-Task Hard-Mixture Curriculum](https://mlsanity.com/paper/2609.25864/) (2026)

## Abstract (arXiv)

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.