{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:30:51Z","timestamp":1790641851664,"version":"4.1.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Research Foundation of South Africa","award":["120409"],"award-info":[{"award-number":["120409"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2022.3229264","type":"journal-article","created":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T18:43:28Z","timestamp":1671043408000},"page":"684-694","source":"Crossref","is-referenced-by-count":17,"title":["Word Segmentation on Discovered Phone Units With Dynamic Programming and Self-Supervised Scoring"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2980-3475","authenticated-orcid":false,"given":"Herman","family":"Kamper","sequence":"first","affiliation":[{"name":"Department of E&amp;E Engineering, Stellenbosch University, Stellenbosch, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639245"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2009.03.008"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3115\/1620754.1620800"},{"key":"ref4","first-page":"184","article-title":"Bootstrapping a unified model of lexical and phonetic acquisition","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics","author":"Elsner","year":"2012"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00146"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2550591"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2019.00092"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2022.3210751"},{"key":"ref9","first-page":"3204","article-title":"Unsupervised word discovery from speech using automatic segmentation into syllable-like units","volume-title":"Proc. Annu. Conf. Int. Speech Commun. Assoc.","author":"Rsnen","year":"2015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.04.008"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269008"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462002"},{"key":"ref13","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1874"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746102"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2904"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2743"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/1687878.1687894"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1171"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM.1985.4795108"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-50"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1112"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268953"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1544"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/1557690.1557736"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-559"},{"key":"ref27","first-page":"40","article-title":"A nonparametric Bayesian approach to acoustic model discovery","volume-title":"Proc. Assoc. Comput. Linguistics","author":"Lee","year":"2012"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p17-3011"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-877"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2224"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1693"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1182"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref35","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baevski","year":"2020"},{"key":"ref36","article-title":"The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","volume-title":"Proc. NeurIPS SAS Workshop","author":"Nguyen","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aaw2594"},{"key":"ref39","article-title":"Unsupervised neural segmentation and clustering for unit discovery in sequential data","volume-title":"Proc. NeurIPS PGR Workshop","author":"Chorowski","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1982.1171472"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2398"},{"key":"ref42","first-page":"1851","article-title":"An improved speech segmentation quality measure: The R-value","volume-title":"Proc. Annu. Conf. Int. Speech Commun. Assoc.","author":"Rsnen","year":"2009"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref44","first-page":"1","article-title":"Phoneme boundary detection using deep bidirectional LSTMs","volume-title":"Proc. Speech Commun. 12. ITG Symp.","author":"Franke","year":"2016"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053053"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1017\/9781108377423.010"},{"key":"ref47","first-page":"42","article-title":"A joint learning model of word segmentation, lexical acquisition and phonetic variability","volume-title":"Proc. Empirical Methods Natural Lang. Process. Conf.","author":"Elsner","year":"2013"},{"issue":"13","key":"ref48","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1023\/A:1007541817488","article-title":"An efficient, probabilistically sound algorithm for segmentation and word discovery","volume":"34","author":"Brent","year":"1999","journal-title":"Mach. Learn."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1111\/desc.12390"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1645"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-638"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2517567"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.09.001"},{"key":"ref54","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163965"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1738"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3000"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00505"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.909282"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1037\/a0039702"},{"key":"ref61","first-page":"1866","article-title":"Unsupervised learning of spoken language with visual context","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Harwath","year":"2016"},{"key":"ref62","first-page":"1309","article-title":"From phonemes to images: Levels of representation in a recurrent neural model of visually-grounded language learning","volume-title":"Proc. COLING Int. Conf. Comput. Linguistics","author":"Gelderloos","year":"2016"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461761"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3180220"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10652"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.insights-1.11"},{"key":"ref67","first-page":"673","article-title":"Bayesian nonparametric hidden semi-Markov models","volume":"14","author":"Johnson","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2438543"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/09984943.pdf?arnumber=9984943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:33:41Z","timestamp":1706758421000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9984943\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3229264","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}