{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:13:57Z","timestamp":1740172437808,"version":"3.37.3"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2020.2996082","type":"journal-article","created":{"date-parts":[[2020,5,20]],"date-time":"2020-05-20T20:52:20Z","timestamp":1590007940000},"page":"1560-1573","source":"Crossref","is-referenced-by-count":1,"title":["Multimodal Word Discovery and Retrieval With Spoken Descriptions and Visual Concepts"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5562-8386","authenticated-orcid":false,"given":"Liming","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5631-2893","authenticated-orcid":false,"given":"Mark","family":"Hasegawa-Johnson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965-7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref33","first-page":"467","article-title":"Class-based N-gram models of natural language","volume":"18","author":"brown","year":"1992","journal-title":"Comput Linguist"},{"key":"ref32","first-page":"252","article-title":"Multilingually trained bottleneck features in spoken language recognition","author":"fer","year":"0","journal-title":"Comput Speech Lang"},{"key":"ref31","first-page":"626","article-title":"EM Algorithms for PCA and SPCA","author":"roweis","year":"1997","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/089120103321337421"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/993268.993313"},{"article-title":"A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models","year":"1998","author":"bilmes","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/S0749-596X(03)00007-X"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953259"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66429-3_7"},{"year":"2017","author":"khokhlov","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424202"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1109"},{"key":"ref15","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1308"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref18","first-page":"263","article-title":"The mathematics of statistical machine translation: Parameter estimation","volume":"19","author":"brown","year":"1993","journal-title":"Comput Linguist"},{"key":"ref19","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682666"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.909282"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462396"},{"year":"2017","author":"kamper","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461545"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1487"},{"key":"ref5","first-page":"40","article-title":"A nonparametric Bayesian approach to acoustic model discovery","author":"lee","year":"0","journal-title":"Proc 50th Annu Meeting Assoc for Comput Linguist Long Papers-Vol 1"},{"key":"ref8","first-page":"641","article-title":"Adaptor grammars: A framework for specifying compositional nonparametric Bayesian models","author":"johnson","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268953"},{"key":"ref2","first-page":"568","article-title":"Unsupervised word discovery from speech using automatic segmentation into syllable-like units","author":"r\u00e4s\u00e4nen","year":"0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-601"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638228"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref22","first-page":"1858","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2872106"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.023"},{"key":"ref23","first-page":"613","article-title":"Representations of language in a model of visually grounded speech signal","author":"chrupa?a","year":"0","journal-title":"Proc 50th Annu Meeting Assoc Comput Linguist (Volume 1 Long Papers)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2517567"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1047"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/09097433.pdf?arnumber=9097433","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:24Z","timestamp":1651080684000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9097433\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.2996082","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2020]]}}}