{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T16:40:54Z","timestamp":1784824854960,"version":"3.55.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1109\/taslp.2022.3180684","type":"journal-article","created":{"date-parts":[[2022,6,7]],"date-time":"2022-06-07T19:34:09Z","timestamp":1654630449000},"page":"2002-2014","source":"Crossref","is-referenced-by-count":22,"title":["Unsupervised Speech Segmentation and Variable Rate Representation Learning Using Segmental Contrastive Predictive Coding"],"prefix":"10.1109","volume":"30","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, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jesus","family":"Villalba","sequence":"additional","affiliation":[{"name":"Center for Language, Speech Processing, Johns Hopkins University, Baltimore, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8245-0413","authenticated-orcid":false,"given":"Piotr","family":"Zelasko","sequence":"additional","affiliation":[{"name":"Center for Language, Speech Processing, Johns Hopkins University, Baltimore, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","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.","author":"Baevski","year":"2020"},{"key":"ref2","first-page":"125","article-title":"WaveNet: A generative model for raw audio","volume-title":"Proc. 9th ISCA Speech Synth. Workshop","author":"Oord","year":"2016"},{"key":"ref3","first-page":"1","article-title":"End-to-end ASR: From supervised to semi-supervised learning with modern architectures","volume-title":"Proc. Int. Conf. Mach. Learn. Workshop","author":"Synnaeve","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-638"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268953"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2904"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.05.001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163965"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855085"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3115\/1557690.1557736"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947338"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2013.05.002"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.04.008"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1476"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269008"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462264"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-80"},{"key":"ref22","first-page":"1","article-title":"Representation learning with contrastive predictive coding","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Oord","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2398"},{"key":"ref25","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":"ref26","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref27","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2020"},{"key":"ref28","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Gutmann","year":"2010"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1874"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1080\/00437956.1954.11659520"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1006\/jmla.1996.0032"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2009.03.008"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9280.00063"},{"key":"ref34","article-title":"Timit acoustic phonetic continuous speech corpus","author":"Garofolo","year":"1993"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.09.001"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-3011"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-877"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-50"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref40","first-page":"1","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baevski","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0085"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2981"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00146"},{"key":"ref44","article-title":"Discovering linguistic structures in speech: Models and applications","author":"Lee","year":"2014"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/S0885-2308(03)00006-8"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref47","first-page":"1","article-title":"Sequence transduction with recurrent neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. Representation Workshop","author":"Graves","year":"2012"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/089976602317318938"},{"key":"ref49","first-page":"1","article-title":"Unsupervised neural segmentation and clustering for unit discovery in sequential data","volume-title":"Proc. NeurIPS Workshop- Percep. Generative Reasoning-Struct., Causality, Probability","author":"Chorowski","year":"2019"},{"key":"ref50","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Oord","year":"2017"},{"key":"ref51","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013"},{"key":"ref52","first-page":"1851","article-title":"An improved speech segmentation quality measure: The R-value","volume-title":"Proc. 10th Annu. Conf. Int. Speech Commun. Assoc.","author":"Rsnen","year":"2009"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1693"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639622"},{"key":"ref55","first-page":"1","article-title":"Unsupervised speech recognition","volume":"34","author":"Baevski","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953257"},{"key":"ref57","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":"ref58","first-page":"1","article-title":"The zero resource speech benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","volume-title":"NeuRIPS Workshop Self-Supervised Learn. Speech Audio Process.","author":"Nguyen","year":"2020"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6570655\/9657755\/9789954-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09789954.pdf?arnumber=9789954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:03:37Z","timestamp":1706756617000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9789954\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3180684","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}