{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:14:19Z","timestamp":1740172459090,"version":"3.37.3"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"JSPS KAKENHI","award":["JP17H06101."],"award-info":[{"award-number":["JP17H06101."]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2020.3042016","type":"journal-article","created":{"date-parts":[[2020,12,2]],"date-time":"2020-12-02T22:45:56Z","timestamp":1606949156000},"page":"348-362","source":"Crossref","is-referenced-by-count":1,"title":["Tackling Perception Bias in Unsupervised Phoneme Discovery Using DPGMM-RNN Hybrid Model and Functional Load"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7054-4589","authenticated-orcid":false,"given":"Bin","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5509-8963","authenticated-orcid":false,"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinsong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-3803","authenticated-orcid":false,"given":"Satoshi","family":"Nakamura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1037\/h0043158"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1121\/1.1906360"},{"key":"ref33","article-title":"Self-consistency as an inductive bias in early language acquisition","volume":"36","author":"fourtassi","year":"0","journal-title":"Proc Annu Meet Cognit Sci Soc"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-1620"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1121\/1.1908024"},{"key":"ref30","first-page":"280","article-title":"Dirichlet process","author":"teh","year":"2010","journal-title":"Encyc of Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846245"},{"key":"ref36","first-page":"1385","article-title":"Sharing clusters among related groups: Hierarchical Dirichlet processes","author":"teh","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","first-page":"641","article-title":"Adaptor grammars: A framework for specifying compositional nonparametric Bayesian models","author":"johnson","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","article-title":"Learning phonetic categories by learning a lexicon","volume":"31","author":"feldman","year":"0","journal-title":"Proc Annu Meet Cognit Sci Soc"},{"key":"ref60","first-page":"3194","article-title":"Using articulatory features and inferred phonological segments in zero resource speech processing","author":"baljekar","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref28","first-page":"620","article-title":"Parallel sampling of DP mixture models using sub-cluster splits","author":"chang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2904"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1007\/s11390-010-9355-8","article-title":"Dirichlet process Gaussian mixture models: Choice of the base distribution","volume":"25","author":"g\u00f6r\u00fcr","year":"2010","journal-title":"J Comput Sci Technol"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/1557690.1557736"},{"key":"ref1","first-page":"40","article-title":"A nonparametric Bayesian approach to acoustic model discovery","author":"lee","year":"0","journal-title":"Proc 50th Annu Meet Assoc Comput Linguistics Long Papers-Volume 1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/00437956.1964.11659830"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1037\/h0020279"},{"journal-title":"A Manual of Phonology","year":"1955","author":"hockett","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1126\/science.167.3917.392"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1006\/jmla.1998.2571"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.6.1.110"},{"key":"ref50","first-page":"639","article-title":"A constructive definition of Dirichlet priors","author":"sethuraman","year":"1994","journal-title":"Statistica Sinica"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1080\/00437956.1967.11435484"},{"key":"ref59","first-page":"637","article-title":"Speech acoustic unit segmentation using hierarchical Dirichlet processes","author":"torbati","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1337"},{"key":"ref57","first-page":"1878","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref56","first-page":"6306","article-title":"Neural discrete representation learning","author":"oord","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2003.09.005"},{"key":"ref54","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"article-title":"ABX-discriminability measures and applications","year":"2016","author":"schatz","key":"ref53"},{"key":"ref52","first-page":"410","article-title":"V-measure: A conditional entropy-based external cluster evaluation measure","author":"rosenberg","year":"0","journal-title":"Proc Joint Conf Empirical Methods Natural Lang Process Comput Natural Lang Learn"},{"key":"ref10","first-page":"3179","article-title":"A hybrid dynamic time warping-deep neural network architecture for unsupervised acoustic modeling","author":"thiolliere","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3232"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1830"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68456-7_14"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.033"},{"key":"ref14","first-page":"488","author":"ebbers","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269011"},{"key":"ref16","first-page":"3189","article-title":"Parallel inference of Dirichlet process Gaussian mixture models for unsupervised acoustic modeling: A feasibility study","author":"chen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref17","first-page":"1","author":"wu","year":"0","journal-title":"Proc Spoken Lang Technol Under-Resourced Lang"},{"key":"ref18","article-title":"DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1","volume":"93","author":"garofolo","year":"1993","journal-title":"NASA STI\/Recon Techn Rep n"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.1906875"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163965"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947338"},{"key":"ref6","first-page":"3169","article-title":"The zero resource speech challenge 2015","author":"versteegh","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.909282"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855085"},{"key":"ref7","first-page":"3199","article-title":"A comparison of neural network methods for unsupervised representation learning on the zero resource speech challenge","author":"renshaw","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref49","first-page":"1","article-title":"Evaluating speech features with the minimal-pair ABX task: Analysis of the classical MFC\/PLP pipeline","author":"schatz","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref9","first-page":"3174","article-title":"Discovering discrete subword units with binarized Autoencoders and hidden-Markov-model encoders","author":"badino","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2010.5684912"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1159\/000258556"},{"key":"ref48","article-title":"Economie des changements phonétiques","author":"andr\u00e9","year":"1955","journal-title":"Berne Francke"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1075\/cilt.279.05sur"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-988"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461648"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e91-d.3.508"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.032"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09276474.pdf?arnumber=9276474","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T15:58:23Z","timestamp":1642003103000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9276474\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.3042016","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2021]]}}}