{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T05:54:13Z","timestamp":1778738053664,"version":"3.51.4"},"reference-count":52,"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:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100009619","name":"Japan Agency for Medical Research and Development","doi-asserted-by":"publisher","award":["JP21dk0310114"],"award-info":[{"award-number":["JP21dk0310114"]}],"id":[{"id":"10.13039\/100009619","id-type":"DOI","asserted-by":"publisher"}]},{"name":"JPNP20006, commissioned by NEDO"}],"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.2024.3402557","type":"journal-article","created":{"date-parts":[[2024,5,17]],"date-time":"2024-05-17T17:54:57Z","timestamp":1715968497000},"page":"2777-2789","source":"Crossref","is-referenced-by-count":3,"title":["Pretraining and Adaptation Techniques for Electrolaryngeal Speech Recognition"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9118-2994","authenticated-orcid":false,"given":"Lester Phillip","family":"Violeta","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6564-4571","authenticated-orcid":false,"given":"Ding","family":"Ma","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3172-3335","authenticated-orcid":false,"given":"Wen-Chin","family":"Huang","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8146-1279","authenticated-orcid":false,"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Information Technology Center, Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1976.10159"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref4","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Graves","year":"2014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0021-9924(00)00023-X"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/000348948008900608"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2147\/MDER.S133225"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64206-2_57"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095931"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707735"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.1997.648252"},{"key":"ref13","article-title":"Speech enhancement for disordered and substitution voices","author":"Hagmller","year":"2009"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1044\/2019_JSLHR-S-18-0313"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10043"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1427"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1384"},{"key":"ref21","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref23","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-168"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746585"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414869"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-480"},{"key":"ref30","article-title":"Sentence encoders on STILTs: Supplementary training on intermediate labeled-data tasks","author":"Phang","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6282"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.554"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21295"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.504"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1296"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413425"},{"key":"ref41","article-title":"Corpus of spontaneous Japanese: Its design and evaluation","volume-title":"Proc. ISCA, IEEE Workshop Spontaneous Speech Process. Recognit.","author":"Maekawa","year":"2003"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/DSLW51110.2021.9523402"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1066"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747550"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"issue":"86","key":"ref50","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref51","article-title":"JSUT corpus: Free large-scale Japanese speech corpus for end-to-end speech synthesis","author":"Sonobe","year":"2017"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC58517.2023.10317318"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10533680.pdf?arnumber=10533680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T17:56:00Z","timestamp":1717091760000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10533680\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3402557","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}