{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:31:12Z","timestamp":1761895872661,"version":"build-2065373602"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209789","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Content-Style Disentangled Audio Style Transfer via Diffusion Model"],"prefix":"10.1109","author":[{"given":"Yiran","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Jiasheng","family":"Lu","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd.,Shenzhen,China"}]},{"given":"Jun","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Xinyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Yingshan","family":"Liang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Zhicheng","family":"Du","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Qingyang","family":"Shi","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Shao-Lun","family":"Huang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3361474"},{"key":"ref2","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023","journal-title":"ICML"},{"article-title":"Audio prompt adapter: Unleashing music editing abilities for text-to-music with lightweight finetuning","year":"2024","author":"Tsai","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3597477"},{"article-title":"Foleycrafter: Bring silent videos to life with lifelike and synchronized sounds","year":"2024","author":"Zhang","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096458"},{"article-title":"St-ito: Controlling audio effects for style transfer with inference-time optimization","year":"2024","author":"Steinmetz","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445962"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"article-title":"Global rhythm style transfer without text transcriptions","year":"2021","author":"Qian","key":"ref11"},{"key":"ref12","article-title":"Unsupervised speech decomposition via triple information bottleneck","author":"Qian","year":"2020","journal-title":"ICML"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447380"},{"article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","year":"2023","author":"Chu","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref16","first-page":"71340","article-title":"Audit: Audio editing by following instructions with latent diffusion models","volume":"36","author":"Wang","year":"2023","journal-title":"NIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2194"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27810"},{"key":"ref19","article-title":"Zero-shot voice style transfer with only autoencoder loss","volume":"abs\/1905.05879","author":"Qian","year":"2019"},{"article-title":"Instantstyle: Free lunch towards style-preserving in text-to-image generation","year":"2024","author":"Wang","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"ref22","article-title":"Foley sound synthesis at the dcase 2023 challenge","volume":"abs\/2304.12521","author":"Choi","year":"2023"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209789.pdf?arnumber=11209789","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T06:00:51Z","timestamp":1761890451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209789\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209789","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}