{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:45:10Z","timestamp":1772905510995,"version":"3.50.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JSPS KAKENHI","award":["22K12089"],"award-info":[{"award-number":["22K12089"]}]},{"name":"JSPS KAKENHI","award":["23H00490"],"award-info":[{"award-number":["23H00490"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3434445","type":"journal-article","created":{"date-parts":[[2024,7,26]],"date-time":"2024-07-26T17:44:05Z","timestamp":1722015845000},"page":"3867-3880","source":"Crossref","is-referenced-by-count":8,"title":["ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Tasks"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1145-0914","authenticated-orcid":false,"given":"Nakamasa","family":"Inoue","sequence":"first","affiliation":[{"name":"Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan"}]},{"given":"Shinta","family":"Otake","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan"}]},{"given":"Takumi","family":"Hirose","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan"}]},{"given":"Masanari","family":"Ohi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tokyo Institute of Technology, Tokyo, Japan"}]},{"given":"Rei","family":"Kawakami","sequence":"additional","affiliation":[{"name":"Department of Systems and Control Engineering, Tokyo Institute of Technology, Tokyo, Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref2","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref3","first-page":"10937","article-title":"UniSpeech: Unified speech representation learning with labeled and unlabeled data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747077"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref7","first-page":"18003","article-title":"ContentVec: An improved self-supervised speech representation by disentangling speakers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-391"},{"key":"ref10","first-page":"1","article-title":"Augmentation adversarial training for unsupervised speaker recognition","volume-title":"Proc. NeurIPS Workshop Self-Supervised Learn. Speech Audio Process.","author":"Huh","year":"2020"},{"key":"ref11","first-page":"1641","article-title":"Semi-supervised contrastive learning with generalized contrastive loss and its application to speaker recognition","volume-title":"Proc. Asia-Pacific Signal Inf. Process. Assoc. Annu. Conf. Summit","author":"Inoue","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746952"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11460"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-453"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.3"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414999"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-110"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.91"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-120"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/549"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-023-00312-8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-419"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447984"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref28","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.41"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076863"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3250825"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414959"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3138674"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1390"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3198546"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.103"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746223"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10023274"},{"key":"ref41","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref43","article-title":"What all do audio transformer models hear? Probing acoustic representations for language delivery and its structure","author":"Shah","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096311"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref46","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref47","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.427"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947357"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-64"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.02.013"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3389631"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10612215.pdf?arnumber=10612215","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T04:05:12Z","timestamp":1725163512000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10612215\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3434445","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}