cs.SDNov 7, 2026

Steer Unified Audio Editing Toward Reliable Source Selection

Authors: Youquan Fu, Dongnuan Cai, Yu Pan, Henghui Du, Yujia Zhang, Ping Luo, Quande Liu, Yake Wei, 

Organizations: Renmin University of China · Tencent · The University of Hong Kong · The Chinese University of Hong Kong

Abstract

Unified audio editors support diverse operations, yet often struggle to modify the intended source while preserving non-target content. We show that source selection in audio editing is shaped by early denoising states, while incorrect early selections can hardly be corrected during subsequent denoising. Motivated by these findings, we propose Source-selection Training via Early-trajectory Emphasis and Recovery (STEER), a two-stage post-training algorithm for reliable selective audio editing. STEER-Emphasis prioritizes training on task-critical early states to reduce source-selection errors, while STEER-Recovery learns corrective denoising from self-generated rollout states to recover from early deviations. To systematically assess source-selection reliability, we introduce the Selective Audio Editing Benchmark, enabling large-scale automatic evaluation of target manipulation and non-target preservation. Applying STEER to our pretrained multitask base editor gives SteerSound, a unified audio editor with leading selective editing performance among open-source audio editors. Experiments on our base editor, UNISON, and SAM Audio demonstrate that STEER consistently improves both selective editing capability and overall editing performance. Early-trajectory emphasis further brings substantial improvements in transcript-conditioned target speaker removal and separation, highlighting the broader applicability of this training principle.

Figures & tables

Explore similar work

Jun 5, 2026

DirectAudioEdit: Inversion-Free Text-Guided Audio Editing via Diffusion Prediction Contrast

Text-guided audio editing aims to modify the language-specified acoustic content while preserving edit-irrelevant source components. Existing training-free methods typically rely on inversion-based editing. While inversion-free editing is appealing as it decreases computational overhead and reconstruction errors, it remains largely unexplored for audio editing. The key challenge is to construct a source-to-target editing path through diffusion denoising dynamics. In this paper, we introduce DirectAudioEdit, the first attempt to develop a training-free and inversion-free method for audio editing. Experiments on music and event-level benchmarks across two backbones show that DirectAudioEdit reduces macro-averaged FAD and KL by 15.9% and 15.8% compared with DDPM inversion, while achieving up to 64.5% editing speedup.
Jun 13, 2026

FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing

Text-to-audio (TTA) generation has made significant strides, yet achieving precise and consistent audio editing remains a major challenge. However, existing methods struggle to balance temporal consistency with background preservation. In this paper, we propose FreeSonic, a training-free framework leveraging the state-of-the-art Rectified Flow-based TangoFlux model. FreeSonic utilizes an optimized inversion-reverse process and joint text-audio attention maps for precise target segment extraction. For content editing, a novel scheduled attention decoupling confines modifications to target regions while preserving original acoustic context. Furthermore, task-oriented noise injection enhances versatility for tasks such as audio removal and non-rigid replacement. Extensive experimental results demonstrate that FreeSonic achieves a superior balance by providing a high-fidelity and efficient solution for precise and consistent audio editing. Project and demos: https://free-sonic.github.io/
Jun 13, 2026

AUDEDIT: Inversion-Free Text-Guided Editing with Pretrained Audio Flow Models

We introduce AudEdit, an inversion-free method for text-guided editing of real audio with a pretrained rectified-flow audio generator. Text-to-audio systems such as Stable Audio 3 already expose audio-to-audio editing by noising an input recording and denoising it under a new prompt, but this inversion-style route must trade prompt adherence against preservation of rhythm, transients, timbre, and long-range musical structure. Motivated by recent inversion-free flow editing in computer vision, we develop an audio-specific direct source-to-target ordinary differential equation for one-dimensional Stable Audio 3 latents: at each flow step, we compare the target- and source-conditioned velocity fields under a shared stochastic source marginal, and update the edited latent by their difference. The resulting editor requires no training, no paired edit data, no optimization, and no access to internal attention maps. Across sound-effect and music editing sets built from FSD50K and the Song Describer Dataset, AudEdit improves CLAP text alignment and audio preservation over SDEdit, ODE inversion, and FireFlow; for example, on sound effects it raises target-text CLAP similarity from 0.42 to 0.52 over the strongest baseline while reducing FAD from 65.70 to 50.37.