{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:23:02Z","timestamp":1775229782025,"version":"3.50.1"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001652","name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001652","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832252","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Personalizing Large Sequence-to-Sequence Speech Foundation Models With Speaker Representations"],"prefix":"10.1109","author":[{"given":"Dominik","family":"Wagner","sequence":"first","affiliation":[{"name":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany"}]},{"given":"Ilja","family":"Baumann","sequence":"additional","affiliation":[{"name":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany"}]},{"given":"Thomas","family":"Ranzenberger","sequence":"additional","affiliation":[{"name":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany"}]},{"given":"Korbinian","family":"Riedhammer","sequence":"additional","affiliation":[{"name":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany"}]},{"given":"Tobias","family":"Bocklet","sequence":"additional","affiliation":[{"name":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref3","article-title":"Robust Speech Recognition via Large-Scale Weak Supervision","author":"Radford","year":"2022","journal-title":"arXiv:2212.04356"},{"key":"ref4","article-title":"UniAudio: An Audio Foundation Model Toward Universal Audio Generation","author":"Yang","year":"2023","journal-title":"arXiv:2310.00704"},{"key":"ref5","article-title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","author":"Yu","year":"2023","journal-title":"arXiv:2303.01037"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2193"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1354"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1505"},{"key":"ref10","first-page":"2790","article-title":"Parameter-Efficient Transfer Learning for NLP","author":"Houlsby","year":"2019","journal-title":"ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref13","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref14","article-title":"Adaptive Budget Allocation for Parameter-Efficient FineTuning","author":"Zhang","year":"2023","journal-title":"ICLR"},{"key":"ref15","article-title":"DoRA: Weight-Decomposed Low-Rank Adaptation","author":"Liu","year":"2024","journal-title":"arXiv:2402.09353"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"ref17","article-title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","author":"Xu","year":"2023","journal-title":"arXiv:2312.12148"},{"key":"ref18","article-title":"Listen, Think, and Understand","author":"Gong","year":"2024","journal-title":"ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.309"},{"key":"ref20","first-page":"18090","article-title":"Pengi: An Audio Language Model for Audio Tasks","volume":"36","author":"Deshmukh","year":"2023","journal-title":"NeurIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446224"},{"key":"ref22","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023","journal-title":"arXiv:2311.07919"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-460"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688231"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-253"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389710"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.541"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447004"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389738"},{"issue":"4","key":"ref32","first-page":"788","article-title":"FrontEnd Factor Analysis for Speaker Verification","volume":"19","author":"Dehak","year":"2011","journal-title":"IEEE TASLP"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10896"},{"key":"ref35","first-page":"12449","article-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref36","article-title":"Adapting SelfSupervised Models to Multi-Talker Speech Recognition Using Speaker Embeddings","author":"Huang","year":"2023","journal-title":"ICASSP"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/SLaTE.2023-27"},{"key":"ref38","first-page":"102","article-title":"LMELECTURES: a multimedia corpus of academic spoken English","volume-title":"SLAM Workshop","author":"Riedhammer"},{"key":"ref39","first-page":"393","article-title":"Verbmobil-Translation of Face-To-Face Dialogs","author":"Wahlster","year":"1993","journal-title":"17. Fachtagung f\u00fcr K\u00fcnstliche Intelligenz"},{"key":"ref40","article-title":"Switchboard-1 Release 2","author":"Godfrey","year":"1993"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref44","article-title":"Decoupled weight decay regularization","author":"Loshchilov","journal-title":"I C L R, 2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003979"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1044\/2019_JSLHR-19-00057"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2023.01.012"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.12.003"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832252.pdf?arnumber=10832252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:14:56Z","timestamp":1737101696000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832252\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832252","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}