{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:46:50Z","timestamp":1778082410180,"version":"3.51.4"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887821","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["AudioEditor: A Training-Free Diffusion-Based Audio Editing Framework"],"prefix":"10.1109","author":[{"given":"Yuhang","family":"Jia","sequence":"first","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Chen","sequence":"additional","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinghua","family":"Zhao","sequence":"additional","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiwan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjia","family":"Zeng","sequence":"additional","affiliation":[{"name":"Lingxi (Beijing) Technology Co., Ltd.,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Chen","sequence":"additional","affiliation":[{"name":"Lingxi (Beijing) Technology Co., Ltd.,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Qin","sequence":"additional","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh"},{"key":"ref5","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"Storydiffusion: Consistent self-attention for long-range image and video generation","author":"Zhou","year":"2024"},{"key":"ref7","first-page":"21450","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref9","first-page":"13916","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"International Conference on Machine Learning","author":"Huang"},{"key":"ref10","article-title":"Make-an-audio 2: Temporal-enhanced text-to-audio generation","author":"Huang","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681688"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3485485"},{"key":"ref14","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Sdedit: Image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021"},{"key":"ref16","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"The Eleventh International Conference on Learning Representations","author":"Hertz"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01185"},{"key":"ref18","article-title":"Get what you want, not what you don\u2019t: Image content suppression for text-to-image diffusion models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Li"},{"key":"ref19","first-page":"71340","article-title":"Audit: Audio editing by following instructions with latent diffusion models","volume":"36","author":"Wang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","article-title":"Wavcraft: Audio editing and generation with natural language prompts","volume-title":"ICLR 2024 Workshop on LLM Agents","author":"Liang"},{"key":"ref21","article-title":"Zero-shot unsupervised and text-based audio editing using DDPM inversion","volume-title":"Forty-first International Conference on Machine Learning","author":"Manor"},{"key":"ref22","article-title":"Prompt-guided precise audio editing with diffusion models","volume-title":"Forty-first International Conference on Machine Learning","author":"Xu"},{"key":"ref23","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.366"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616087"},{"key":"ref29","article-title":"Dreamix: Video diffusion models are general video editors","author":"Molad","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19551-8_23"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887821.pdf?arnumber=10887821","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:44Z","timestamp":1774416164000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887821\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887821","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}