{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:47:20Z","timestamp":1775202440357,"version":"3.50.1"},"reference-count":51,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"The Hong Kong Polytechnic University","award":["RUG7"],"award-info":[{"award-number":["RUG7"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.3014559","type":"journal-article","created":{"date-parts":[[2020,8,5]],"date-time":"2020-08-05T20:46:49Z","timestamp":1596660409000},"page":"2641-2655","source":"Crossref","is-referenced-by-count":2,"title":["Vector-Based Feature Representations for Speech Signals: From Supervector to Latent Vector"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1715-2540","authenticated-orcid":false,"given":"Yuechi","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3921-7074","authenticated-orcid":false,"given":"Frank H. F.","family":"Leung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"273","article-title":"Speech signal representations","author":"huang","year":"2001","journal-title":"Spoken Language Processing A Guide to Theory Algorithm and System Development"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2018.8631583"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.840940"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2003.809034"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2337845"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462122"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(99)00081-3"},{"key":"ref36","article-title":"American English Speech Recognition Corpus (King-ASR-L-081)","year":"2013"},{"key":"ref35","article-title":"The EM algorithm for mixtures of factor analyzers","author":"ghahramani","year":"1996"},{"key":"ref34","first-page":"559","article-title":"Continuous latent variables","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2500730"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1109\/TPAMI.2011.104","article-title":"Probabilistic models for inference about identity","volume":"34","author":"li","year":"2012","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.12928\/telkomnika.v16i1.5731"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/89.365379"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-170"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21236\/ADA613971"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-50"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2793670"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2319159"},{"key":"ref51","first-page":"338","article-title":"Bhattacharyya-based GMM-SVM system with adaptive relevance factor for pair language recognition","author":"you","year":"2012","journal-title":"Proc Odyssey"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref11","first-page":"1","article-title":"Joint plda for simultaneous modeling of two factors","volume":"20","author":"ferrer","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref12","first-page":"5781","article-title":"Who do I sound like? Showcasing speaking recognition technology by youtube voice search","author":"vestman","year":"2019","journal-title":"Proc IEEE Int Conf Acoustic Speech Signal Process"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2925956"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2947199"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2887021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2856373"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2191395"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.870086"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495407"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2462851"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2774505"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2008.2006711"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2911175"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2703939"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2226161"},{"key":"ref48","article-title":"Classification: Basic concepts and techniques","author":"tan","year":"2018","journal-title":"Introduction to Data Mining"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-460"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953195"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8488995"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e88-d.3.418"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383266"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09159906.pdf?arnumber=9159906","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:38Z","timestamp":1652194298000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9159906\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.3014559","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}