{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T21:16:05Z","timestamp":1764018965942,"version":"3.44.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T00:00:00Z","timestamp":1664755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T00:00:00Z","timestamp":1664755200000},"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":[[2022,10,3]]},"DOI":"10.1109\/icccnt54827.2022.9984422","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T14:44:09Z","timestamp":1672065849000},"page":"1-6","source":"Crossref","is-referenced-by-count":17,"title":["Tamil Speech Recognition Using XLSR Wav2Vec2.0 & CTC Algorithm"],"prefix":"10.1109","author":[{"given":"A","family":"Akhilesh","sequence":"first","affiliation":[{"name":"Amrita Vishwa Vidyapeetham,Amrita School of Engineering,Department of Computer Science and Engineering,Bengaluru,India"}]},{"given":"Brinda","family":"P","sequence":"additional","affiliation":[{"name":"Amrita Vishwa Vidyapeetham,Amrita School of Engineering,Department of Computer Science and Engineering,Bengaluru,India"}]},{"given":"Keerthana","family":"S","sequence":"additional","affiliation":[{"name":"Amrita Vishwa Vidyapeetham,Amrita School of Engineering,Department of Computer Science and Engineering,Bengaluru,India"}]},{"given":"Deepa","family":"Gupta","sequence":"additional","affiliation":[{"name":"Amrita Vishwa Vidyapeetham,Amrita School of Engineering,Department of Computer Science and Engineering,Bengaluru,India"}]},{"given":"Susmitha","family":"Vekkot","sequence":"additional","affiliation":[{"name":"Amrita Vishwa Vidyapeetham,Amrita School of Engineering,Department of Electronics & Communication Engineering,Bengaluru,India"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.32604\/iasc.2022.022021"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1016\/j.knosys.2022.108360"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/SLT.2018.8639038"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.21437\/interspeech.2018-1392"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICASSP.2019.8682490"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ICASSP.2019.8683602"},{"key":"ref7","article-title":"Cross-modal transfer learning for multilingual speech-to-text translation","author":"Tran","year":"2020","journal-title":"arXiv preprint arXiv:2010.12829"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.21437\/Interspeech.2020-2404"},{"key":"ref9","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":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/LSP.2020.3044547"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1145\/1143844.1143891"},{"key":"ref12","article-title":"Deep Speech Based End-to-End Automated Speech Recognition (ASR) for Indian-English Accents","author":"Dubey","year":"2022","journal-title":"arXiv preprint arXiv:2204.00977"},{"volume-title":"Facebook","year":"2020","article-title":"Wave2Vec2.0 Large","key":"ref13"},{"volume-title":"Xlsr wav2vec2 english by jonatas grosman","year":"2021","author":"Grosman","key":"ref14"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/IJCNN52387.2021.9533587"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref17","article-title":"End-to-end text-to-speech for low-resource languages by cross-lingual transfer learning","author":"Tu","year":"2019","journal-title":"arXiv preprint arXiv:1904.06508"},{"key":"ref18","article-title":"From english to foreign languages: Transferring pre- trained language models","author":"Tran","year":"2020","journal-title":"arXiv preprint arXiv:2002.07306"},{"key":"ref19","article-title":"An introduction to domain adaptation and transfer learning","author":"Kouw","year":"2018","journal-title":"arXiv preprint arXiv:1812.11806"},{"key":"ref20","article-title":"Applying wav2vec2. 0 to speech recognition in various low-resource languages","author":"Yi","year":"2020","journal-title":"arXiv preprint arXiv:2012.12121"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ICCSP.2018.8524192"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1007\/978-981-19-1324-2_2"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1007\/s40860-021-00140-7"},{"key":"ref24","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019","journal-title":"arXiv preprint arXiv:1912.06670"}],"event":{"name":"2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT)","start":{"date-parts":[[2022,10,3]]},"location":"Kharagpur, India","end":{"date-parts":[[2022,10,5]]}},"container-title":["2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9984157\/9984211\/09984422.pdf?arnumber=9984422","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T19:19:36Z","timestamp":1756235976000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9984422\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,3]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icccnt54827.2022.9984422","relation":{},"subject":[],"published":{"date-parts":[[2022,10,3]]}}}