{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:15:48Z","timestamp":1774419348157,"version":"3.50.1"},"reference-count":31,"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"}],"funder":[{"DOI":"10.13039\/501100003816","name":"Huawei Technologies","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003816","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889172","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["TAGMO: Temporal Control Audio Generation for Multiple Visual Objects Without Training"],"prefix":"10.1109","author":[{"given":"Xinyu","family":"Zhang","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keyu","family":"Fan","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiran","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingshan","family":"Liang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiasheng","family":"Lu","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhicheng","family":"Du","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyang","family":"Shi","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiwu","family":"Qin","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","author":"Huang","year":"2023"},{"key":"ref2","article-title":"Semantically consistent video-to-audio generation using multimodal language large model","volume":"abs\/2404.16305","author":"Chen","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00240"},{"key":"ref4","article-title":"Video-to-audio generation with hidden alignment","volume":"abs\/2407.07464","author":"Xu","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681027"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02537"},{"key":"ref7","article-title":"Simple and controllable music generation","author":"Copet","year":"2023"},{"key":"ref8","article-title":"Audiogen: Textually guided audio generation","author":"Kreuk","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681688"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/502"},{"key":"ref12","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref14","article-title":"Make-an-audio 2: Temporal-enhanced text-to-audio generation","author":"Huang","year":"2023"},{"key":"ref15","article-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024"},{"key":"ref16","article-title":"Diff-foley: Synchronized video-to-audio synthesis with latent diffusion models","author":"Luo","year":"2023"},{"key":"ref17","article-title":"Lumina-t2x: Transforming text into any modality, resolution, and duration via flow-based large diffusion transformers","author":"Gao","year":"2024"},{"key":"ref18","article-title":"Foleycrafter: Bring silent videos to life with lifelike and synchronized sounds","author":"Zhang","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00837"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447048"},{"key":"ref21","article-title":"Mulan: Multimodal-llm agent for progressive and interactive multi-object diffusion","author":"Li","year":"2024"},{"key":"ref22","article-title":"Object-driven one-shot fine-tuning of text-to-image diffusion with prototypical embedding","author":"Lu","year":"2024"},{"key":"ref23","article-title":"ediff-i: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2023"},{"key":"ref24","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29773"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref27","article-title":"Yolov10: Real-time end-to-end object detection","author":"Wang","year":"2024"},{"key":"ref28","article-title":"Bigvgan: A universal neural vocoder with large-scale training","author":"gil Lee","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2219"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.336"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"}],"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\/10889172.pdf?arnumber=10889172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:24Z","timestamp":1774416144000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889172\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889172","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}