{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:13:59Z","timestamp":1740172439255,"version":"3.37.3"},"reference-count":63,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Ministry of Information Technology"},{"name":"Bhashini Program"}],"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.2023.3337670","type":"journal-article","created":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T18:54:12Z","timestamp":1701716052000},"page":"1036-1047","source":"Crossref","is-referenced-by-count":1,"title":["Representation Learning With Hidden Unit Clustering for Low Resource Speech Applications"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9885-5460","authenticated-orcid":false,"given":"Varun","family":"Krishna","sequence":"first","affiliation":[{"name":"Learning and Extraction of Acoustic Patterns Lab, Department of Electrical Engineering, Indian Institute of Science, Bangalore, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7393-0917","authenticated-orcid":false,"given":"Tarun","family":"Sai","sequence":"additional","affiliation":[{"name":"Learning and Extraction of Acoustic Patterns Lab, Department of Electrical Engineering, Indian Institute of Science, Bangalore, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5779-9066","authenticated-orcid":false,"given":"Sriram","family":"Ganapathy","sequence":"additional","affiliation":[{"name":"Learning and Extraction of Acoustic Patterns Lab, Department of Electrical Engineering, Indian Institute of Science, Bangalore, India"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.909282"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1755"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref5","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baevski","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1503"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472808"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.5001926"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2652"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1972"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref13","article-title":"VQ-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baevski","year":"2020"},{"key":"ref14","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref15","article-title":"Representation learning with contrastive predictive coding","volume":"abs\/1807.03748","author":"Van den Oord","year":"2018","journal-title":"CoRR"},{"key":"ref16","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Van Den Oord","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-638"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268953"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2743"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269011"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1693"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269013"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1079"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-854"},{"key":"ref30","first-page":"100","article-title":"MASR: Metadata aware speech representation","volume-title":"Proc. IEEE Autom. Speech Recognit. Understanding Workshop","author":"Raj","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747259"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref36","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"ref38","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chiu","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"issue":"11","key":"ref41","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCSW.2011.20"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1198\/016214503000000666"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-441"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00321"},{"volume-title":"Model Assisted Survey Sampling","year":"2003","author":"Srndal","key":"ref48"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1182"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1465"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.iwslt-1.46"},{"key":"ref52","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions, and reversals","volume-title":"Proc. Sov. Phys. Doklady. Sov. Union","volume":"10","author":"Levenshtein","year":"1966"},{"article-title":"MUSAN: A music, speech, and noise corpus","year":"2015","author":"Snyder","key":"ref53"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.4930"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref57","first-page":"3528","article-title":"Semi-supervised acoustic and language modeling for hindi ASR","volume-title":"Proc. Annu. Conf. Int. Speech Commun. Assoc.","author":"Rath","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326009"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1242"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"year":"2018","key":"ref62","article-title":"Free speech... recognition (linux, windows and mac) - voxforge.org"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10339798.pdf?arnumber=10339798","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T01:49:40Z","timestamp":1705542580000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10339798\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3337670","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2024]]}}}