{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:56:18Z","timestamp":1730199378831,"version":"3.28.0"},"reference-count":36,"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\/asru57964.2023.10389624","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Gated Multi Encoders and Multitask Objectives for Dialectal Speech Recognition in Indian Languages"],"prefix":"10.1109","author":[{"given":"Sathvik","family":"Udupa","sequence":"first","affiliation":[{"name":"Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012"}]},{"given":"Jesuraja","family":"Bandekar","sequence":"additional","affiliation":[{"name":"Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012"}]},{"given":"G","family":"Deekshitha","sequence":"additional","affiliation":[{"name":"Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012"}]},{"given":"Saurabh","family":"Kumar","sequence":"additional","affiliation":[{"name":"Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012"}]},{"given":"Prasanta Kumar","family":"Ghosh","sequence":"additional","affiliation":[{"name":"Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012"}]},{"given":"Sandhya","family":"Badiger","sequence":"additional","affiliation":[{"name":"Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012"}]},{"given":"Abhayjeet","family":"Singh","sequence":"additional","affiliation":[{"name":"Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012"}]},{"given":"Savitha","family":"Murthy","sequence":"additional","affiliation":[{"name":"Indian Institute of Science (IISc),Electrical Engineering Department,Bangalore,India,560012"}]},{"given":"Priyanka","family":"Pai","sequence":"additional","affiliation":[{"name":"Navana Tech (NT),Mumbai,India,400001"}]},{"given":"Srinivasa","family":"Raghavan","sequence":"additional","affiliation":[{"name":"Navana Tech (NT),Mumbai,India,400001"}]},{"given":"Raoul","family":"Nanavati","sequence":"additional","affiliation":[{"name":"Navana Tech (NT),Mumbai,India,400001"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1525\/aa.1961.63.5.02a00060"},{"volume-title":"Patterns of regional geography: an international perspective","author":"Mandal","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2485"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2488"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-555"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096662"},{"key":"ref7","article-title":"Building high-accuracy multilingual asr with gated language experts and curriculum training","author":"Sun","year":"2023","journal-title":"arXiv preprint arXiv:2303.00786"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414451"},{"volume-title":"Multiencoder multi-resolution framework for end-to-end speech recognition","year":"2018","author":"Li","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-923"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461886"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10739"},{"key":"ref15","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"abs\/2006.11477","author":"Baevski","year":"2020","journal-title":"ArXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1280"},{"key":"ref17","article-title":"Speech representation learning through self-supervised pretraining and multitask finetuning","author":"Chen","year":"2021","journal-title":"arXiv preprint arXiv:2110.09930"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11368"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095326"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.692"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1005"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1928"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-srw.36"},{"volume-title":"Model adaptation for asr in low-resource indian languages","year":"2023","author":"Singh","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"volume-title":"Robust speech recognition via large-scale weak supervision","year":"2022","author":"Radford","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad467"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"volume-title":"Scaling speech technology to 1,000 + languages","year":"2023","author":"Pratap","key":"ref33"},{"volume-title":"Clsril-23: Cross lingual speech representations for indic languages","year":"2021","author":"Gupta","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21327"},{"key":"ref36","first-page":"187","article-title":"Kenlm: Faster and smaller language model queries","volume-title":"Proceedings of the sixth workshop on statistical machine translation","author":"Heafield"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2023,12,16]]},"location":"Taipei, Taiwan","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\/10389624.pdf?arnumber=10389624","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:35:29Z","timestamp":1706027729000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389624\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389624","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}