{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:46:16Z","timestamp":1776887176132,"version":"3.51.2"},"reference-count":37,"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\/icassp49660.2025.10887836","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":1,"title":["Keep what you need : extracting efficient subnetworks from large audio representation models"],"prefix":"10.1109","author":[{"given":"David","family":"Genova","sequence":"first","affiliation":[{"name":"IRCAM - Sorbonne University - CNRS,UMR 9912 STMS,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philippe","family":"Esling","sequence":"additional","affiliation":[{"name":"IRCAM - Sorbonne University - CNRS,UMR 9912 STMS,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"Hurlin","sequence":"additional","affiliation":[{"name":"Squarp Instruments,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref3","first-page":"39626","article-title":"Marble: Music audio representation benchmark for universal evaluation","volume":"36","author":"Yuan","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref7","article-title":"Mert: Acoustic music understanding model with large-scale self-supervised training","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yizhi"},{"key":"ref8","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"International conference on machine learning","author":"Houlsby"},{"key":"ref9","article-title":"Optimal brain damage","volume":"2","author":"LeCun","year":"1989","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.l803.03635"},{"key":"ref11","article-title":"Diet deep generative audio models with structured lottery","volume-title":"23rd International Conference on Digital Audio Effects (DAFx-20)","author":"Esling"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref15","first-page":"119","article-title":"Audiocaps: Generating captions for audios in the wild","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Kim"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616087"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448314"},{"key":"ref20","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"International Conference on Machine Learning","author":"Chiu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1108\/RR-08-2013-0197"},{"key":"ref25","first-page":"109","article-title":"Scaling & shifting your features: A new baseline for efficient model tuning","volume":"35","author":"Lian","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298572"},{"key":"ref27","first-page":"3259","article-title":"Linear mode connectivity and the lottery ticket hypothesis","volume-title":"International Conference on Machine Learning","author":"Frankle"},{"key":"ref28","article-title":"Drawing early-bird tickets: Toward more efficient training of deep networks","volume-title":"International Conference on Learning Representations","author":"You"},{"key":"ref29","article-title":"Snip: single-shot network pruning based on connection sensitivity","volume-title":"International Conference on Learning Representations. Open Review","author":"Lee"},{"key":"ref30","article-title":"Ultra-light deep mir by trimming lottery tickets","volume-title":"International Symposium on Music Information Retrieval (ISMIR)","author":"Esling"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref32","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref36","first-page":"387","article-title":"Evaluation of algorithms using games: The case of music tagging","volume-title":"ISMIR","author":"Law"},{"key":"ref37","first-page":"1068","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","volume-title":"International Conference on Machine Learning","author":"Engel"}],"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\/10887836.pdf?arnumber=10887836","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:56Z","timestamp":1774416356000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887836\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887836","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}