{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:12:38Z","timestamp":1774419158539,"version":"3.50.1"},"reference-count":30,"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\/icassp49660.2025.10889683","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Learning Control of Neural Sound Effects Synthesis from Physically Inspired Models"],"prefix":"10.1109","author":[{"given":"Yisu","family":"Zong","sequence":"first","affiliation":[{"name":"Queen Mary University of London,Centre for Digital Music,London,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua","family":"Reiss","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,Centre for Digital Music,London,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2022.0108"},{"key":"ref2","article-title":"A machine learning method to evaluate and improve sound effects synthesis model design","volume-title":"Audio Engineering Society Conference: AES International Audio for Games Conference","author":"Zong"},{"key":"ref3","article-title":"Adversarial audio synthesis","volume-title":"International Conference on Learning Representations","author":"Donahue"},{"key":"ref4","article-title":"Wavenet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref5","article-title":"Rave: A variational autoencoder for fast and high-quality neural audio synthesis","author":"Caillon","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447380"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v18i1.21941"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-03789-4_20"},{"key":"ref9","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":"ref10","article-title":"Synthesising knocking sound effects using conditional wavegan","volume-title":"SMC Sound and Music Computing Conference","author":"Barahona-Rios"},{"key":"ref11","article-title":"Ddsp: Differentiable digital signal processing","volume-title":"International Conference on Learning Representations","author":"Engel"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3364616"},{"key":"ref13","article-title":"Drumgan: Synthesis of drum sounds with timbral feature conditioning using generative adversarial networks","volume-title":"International Society for Music Information Retrieval Conference","author":"Nistal"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096670"},{"key":"ref15","article-title":"A general framework for learning procedural audio models of environmental sounds","author":"Serrano","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3393741"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref18","volume-title":"Designing sound.","author":"Farnell","year":"2010"},{"key":"ref19","article-title":"Durian: Duration informed attention network for multi-modal synthesis","author":"Yu","year":"2019"},{"key":"ref20","article-title":"Auto-encoding variational bayes","volume-title":"International Conference on Learning Representations","author":"Kingma"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref22","article-title":"Fader networks: Manipulating images by sliding attributes","volume":"30","author":"Lample","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref23","first-page":"670","article-title":"Attributes-aware deep music transformation","volume-title":"International Society for Music Information Retrieval Conference","author":"Kawai"},{"key":"ref24","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"Kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref26","article-title":"Timbretron: A wavenet (cyclegan (cqt (audio))) pipeline for musical timbre transfer","volume-title":"International Conference on Learning Representations","author":"Huang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414760"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"},{"issue":"1","key":"ref29","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"The Journal of Machine Learning Research"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"}],"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\/10889683.pdf?arnumber=10889683","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:20:56Z","timestamp":1774416056000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889683\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889683","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}