{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T10:05:37Z","timestamp":1764842737008,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095644","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["Domain and Language Adaptation Using Heterogeneous Datasets for Wav2vec2.0-Based Speech Recognition of Low-Resource Language"],"prefix":"10.1109","author":[{"given":"Kak","family":"Soky","sequence":"first","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Li","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology (NICT),Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenhui","family":"Chu","sequence":"additional","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747667"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746952"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref15","article-title":"Attention is All You Need","author":"vaswani","year":"2017","journal-title":"Proc Neurlps"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"4508","DOI":"10.21437\/Interspeech.2021-1852","article-title":"Speech Emotion Recognition with MultiTask Learning","author":"cai","year":"2021","journal-title":"Proc INTERSPEECH"},{"article-title":"Layer Normalization","year":"2016","author":"ba","key":"ref20"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10896"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1142\/S2717554522500072"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10270"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/O-COCOSDA202152914.2021.9660421"},{"key":"ref2","article-title":"vqwav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019","journal-title":"CoRR"},{"key":"ref1","first-page":"12449","article-title":"wav2vec 2.0: A Framework for SelfSupervised Learning of Speech Representations","volume":"33","author":"baevski","year":"2020","journal-title":"Proc Neurlps"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref18","article-title":"On the use of speaker information for automatic speech recognition in speaker-imbalanced corpora","author":"soky","year":"2021","journal-title":"Proc APSIPA ASC"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-631"},{"article-title":"Applying wav2vec2.0 to speech recognition in various low-resource languages","year":"2020","author":"yi","key":"ref7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3071668"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref6","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc ACL"},{"article-title":"Robust speech recognition via large-scale weak supervision","year":"2022","author":"xu","key":"ref5"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095644.pdf?arnumber=10095644","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T22:07:10Z","timestamp":1729375630000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095644\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095644","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}