Saved in:
Bibliographic Details
Main Authors: Gao, Liting, Yuan, Yi, Chen, Yaru, Cheng, Yuelan, Li, Zhenbo, Wen, Juan, Zhang, Shubin, Wang, Wenwu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.14003
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910132235927552
author Gao, Liting
Yuan, Yi
Chen, Yaru
Cheng, Yuelan
Li, Zhenbo
Wen, Juan
Zhang, Shubin
Wang, Wenwu
author_facet Gao, Liting
Yuan, Yi
Chen, Yaru
Cheng, Yuelan
Li, Zhenbo
Wen, Juan
Zhang, Shubin
Wang, Wenwu
contents Diffusion models have shown remarkable progress in text-to-audio generation. However, text-guided audio editing remains in its early stages. This task focuses on modifying the target content within an audio signal while preserving the rest, thus demanding precise localization and faithful editing according to the text prompt. Existing training-based and zero-shot methods that rely on full-caption or costly optimization often struggle with complex editing or lack practicality. In this work, we propose a novel end-to-end efficient rectified flow matching-based diffusion framework for audio editing, and construct a dataset featuring overlapping multi-event audio to support training and benchmarking in complex scenarios. Experiments show that our model achieves faithful semantic alignment without requiring auxiliary captions or masks, while maintaining competitive editing quality across metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2509_14003
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RFM-Editing: Rectified Flow Matching for Text-guided Audio Editing
Gao, Liting
Yuan, Yi
Chen, Yaru
Cheng, Yuelan
Li, Zhenbo
Wen, Juan
Zhang, Shubin
Wang, Wenwu
Sound
Artificial Intelligence
Diffusion models have shown remarkable progress in text-to-audio generation. However, text-guided audio editing remains in its early stages. This task focuses on modifying the target content within an audio signal while preserving the rest, thus demanding precise localization and faithful editing according to the text prompt. Existing training-based and zero-shot methods that rely on full-caption or costly optimization often struggle with complex editing or lack practicality. In this work, we propose a novel end-to-end efficient rectified flow matching-based diffusion framework for audio editing, and construct a dataset featuring overlapping multi-event audio to support training and benchmarking in complex scenarios. Experiments show that our model achieves faithful semantic alignment without requiring auxiliary captions or masks, while maintaining competitive editing quality across metrics.
title RFM-Editing: Rectified Flow Matching for Text-guided Audio Editing
topic Sound
Artificial Intelligence
url https://arxiv.org/abs/2509.14003