{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T21:32:58Z","timestamp":1781818378797,"version":"3.54.5"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389710","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:38:40Z","timestamp":1705671520000},"page":"1-6","source":"Crossref","is-referenced-by-count":5,"title":["Speaker Adaptation for End-to-End Speech Recognition Systems in Noisy Environments"],"prefix":"10.1109","author":[{"given":"Dominik","family":"Wagner","sequence":"first","affiliation":[{"name":"Technische Hochschule N&#x00FC;rnberg Georg Simon Ohm,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ilja","family":"Baumann","sequence":"additional","affiliation":[{"name":"Technische Hochschule N&#x00FC;rnberg Georg Simon Ohm,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian P.","family":"Bayerl","sequence":"additional","affiliation":[{"name":"Technische Hochschule N&#x00FC;rnberg Georg Simon Ohm,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Korbinian","family":"Riedhammer","sequence":"additional","affiliation":[{"name":"Technische Hochschule N&#x00FC;rnberg Georg Simon Ohm,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Bocklet","sequence":"additional","affiliation":[{"name":"Technische Hochschule N&#x00FC;rnberg Georg Simon Ohm,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Evaluation of feature-space speaker\u2018 adaptation for end-to-end acoustic models","volume-title":"Proc. LREC","author":"Tomashenko"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462161"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659609"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003844"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660239"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639212"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682510"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854823"},{"key":"ref12","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref13","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":"NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1281"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-211"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-680"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10723"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10723"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003844"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1130"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10896"},{"key":"ref23","volume-title":"Investigation of speaker-adaptation methods in transformer based asr","author":"Shetty","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054249"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1438"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462161"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref28","volume-title":"Switchboard-1 release 2","author":"Godfrey","year":"1993"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref32","article-title":"MUSAN: A Music, Speech, and Noise Corpus","author":"Snyder","year":"2015","journal-title":"arXiv:1510.08484v1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref34","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"37","author":"Ioffe","year":"2015","journal-title":"ICML"},{"issue":"56","key":"ref35","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR 2015"},{"key":"ref38","volume-title":"Adadelta: An adaptive learning rate method","author":"Zeiler","year":"2012"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref40","volume-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref41","article-title":"The Fisher corpus: a resource for the next generations of speech-to-text","author":"Cieri","year":"2004","journal-title":"LREC"},{"key":"ref42","article-title":"The Kaldi speech recognition toolkit","author":"Povey","year":"2011","journal-title":"2011 IEEE ASRU"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-595"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1280"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389710.pdf?arnumber=10389710","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T11:31:55Z","timestamp":1706009515000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389710\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389710","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}