{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T05:15:20Z","timestamp":1773119720854,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447380","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"6820-6824","source":"Crossref","is-referenced-by-count":15,"title":["T-Foley: A Controllable Waveform-Domain Diffusion Model for Temporal-Event-Guided Foley Sound Synthesis"],"prefix":"10.1109","author":[{"given":"Yoonjin","family":"Chung","sequence":"first","affiliation":[{"name":"KAIST,Graduate School of Artificial Intelligence,Republic of Korea"}]},{"given":"Junwon","family":"Lee","sequence":"additional","affiliation":[{"name":"KAIST,Graduate School of Artificial Intelligence,Republic of Korea"}]},{"given":"Juhan","family":"Nam","sequence":"additional","affiliation":[{"name":"KAIST,Graduate School of Artificial Intelligence,Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","first-page":"16","article-title":"Foley sound synthesis at the DCASE 2023 challenge","volume-title":"Proceedings of the 8th Detection and Classification of Acoustic Scenes and Events 2023 Workshop (DCASE2023)","author":"Choi"},{"key":"ref2","article-title":"Neural synthesis of footsteps sound effects with generative adversarial networks","author":"Comunit\u00e0","year":"2022","journal-title":"Audio Engineering Society Convention 152"},{"key":"ref3","article-title":"Generating diverse realistic laughter for interactive art","author":"Afsar","year":"2021"},{"key":"ref4","first-page":"590","article-title":"DRUMGAN: synthesis of drum sounds with timbral feature conditioning using generative adversarial networks","volume-title":"Proc. of the 21th Int. Soc. for Music Information Retrieval Conf. (ISMIR)","author":"Nistal"},{"key":"ref5","first-page":"579","article-title":"Crash: raw audio score-based generative modeling for controllable high-resolution drum sound synthesis","volume-title":"Proc. of the Int. Soc. for Music Information Retrieval Conf. (ISMIR)","author":"Rouard"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3005033"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00240"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596430"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3177894"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3009820"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096760"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref13","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref14","article-title":"Audiogen: Textually guided audio generation","volume-title":"The Eleventh International Conference on Learning Representations","author":"Kreuk"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096353"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref17","article-title":"Wavegrad: Estimating gradients for waveform generation","volume-title":"International Conference on Learning Representations","author":"Chen"},{"key":"ref18","article-title":"Temporal film: Capturing long-range sequence dependencies with feature-wise modulations","volume":"32","author":"Birnbaum","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","first-page":"148","article-title":"Vocal Imitation Set: a dataset of vocally imitated sound events using the audioset ontology","volume-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2018 Workshop (DCASE2018)","author":"Kim"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702387"},{"key":"ref21","first-page":"21696","article-title":"Variational diffusion models","volume":"34","author":"Kingma","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447380.pdf?arnumber=10447380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:33:36Z","timestamp":1722573216000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447380\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447380","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}