{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T16:06:59Z","timestamp":1773418019876,"version":"3.50.1"},"reference-count":50,"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":"am","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":"NSF","award":["1909075"],"award-info":[{"award-number":["1909075"]}]}],"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.2024.3350888","type":"journal-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T21:30:17Z","timestamp":1705354217000},"page":"4277-4287","source":"Crossref","is-referenced-by-count":2,"title":["Slowness Regularized Contrastive Predictive Coding for Acoustic Unit Discovery"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6477-3895","authenticated-orcid":false,"given":"Saurabhchand","family":"Bhati","sequence":"first","affiliation":[{"name":"Center for Language, Speech Processing, Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9459-8426","authenticated-orcid":false,"given":"Jes\u00fas","family":"Villalba","sequence":"additional","affiliation":[{"name":"Center for Language, Speech Processing, Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8245-0413","authenticated-orcid":false,"given":"Piotr","family":"\u017belasko","sequence":"additional","affiliation":[{"name":"Meaning.Team Inc., Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3033-7005","authenticated-orcid":false,"given":"Laureano","family":"Moro-Velazquez","sequence":"additional","affiliation":[{"name":"Center for Language, Speech Processing, Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4489-5753","authenticated-orcid":false,"given":"Najim","family":"Dehak","sequence":"additional","affiliation":[{"name":"Center for Language, Speech Processing, Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-80"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163965"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855085"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/1557690.1557736"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947338"},{"key":"ref8","first-page":"40","article-title":"A nonparametric Bayesian approach to acoustic model discovery","volume-title":"Proc. 50th Annu. Meeting Assoc. Comput. Linguistics, Long Papers","volume":"1","author":"Lee","year":"2012"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2013.05.002"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.04.008"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1476"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269008"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462264"},{"key":"ref14","first-page":"1","article-title":"Representation learning with contrastive predictive coding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Oord","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref16","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.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref18","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin","year":"2019"},{"key":"ref19","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1862"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1874"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1544"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746102"},{"key":"ref27","first-page":"34995","article-title":"Variable-rate hierarchical CPC leads to acoustic unit discovery in speech","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Cuervo","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3000"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383605"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-638"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.031"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268953"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2904"},{"key":"ref35","first-page":"1","article-title":"The zero resource speech challenge 2021: Spoken language modelling","volume-title":"Proc. NeuRIPS Workshop Self-Supervised Learn. Speech Audio Process.","author":"Dunbar","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683639"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-644"},{"key":"ref38","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref39","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Oord","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2398"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1693"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/089976602317318938"},{"key":"ref43","first-page":"1","article-title":"Unsupervised neural segmentation and clustering for unit discovery in sequential data","volume-title":"Proc. NeurIPS 2019 Workshop- Percep. Generative Reasoning-Struct., Causality, Probability","author":"Chorowski","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-50"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3229264"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3180684"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-441"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269011"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1182"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6570655\/10304349\/10400460-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10400460.pdf?arnumber=10400460","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T18:26:01Z","timestamp":1727893561000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10400460\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3350888","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}