{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T14:32:42Z","timestamp":1746455562486,"version":"3.37.3"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2017,4,1]],"date-time":"2017-04-01T00:00:00Z","timestamp":1491004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100000266","name":"EPSRC","doi-asserted-by":"publisher","award":["EP\/I031022\/1"],"award-info":[{"award-number":["EP\/I031022\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Speech Technology"},{"DOI":"10.13039\/100011039","name":"Intelligence Advanced Research Projects Activity (IARPA)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011039","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Department of Defense U.S. Army Research Laboratory (DoD\/ARL) Contract","award":["W911NF-12-C-0012"],"award-info":[{"award-number":["W911NF-12-C-0012"]}]},{"name":"Singapore Ministry of Education Academic Research Fund Tier 2","award":["MOE2014-T2-1-068"],"award-info":[{"award-number":["MOE2014-T2-1-068"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2017,4]]},"DOI":"10.1109\/taslp.2017.2670141","type":"journal-article","created":{"date-parts":[[2017,2,16]],"date-time":"2017-02-16T19:14:20Z","timestamp":1487272460000},"page":"818-828","source":"Crossref","is-referenced-by-count":4,"title":["I-Vectors and Structured Neural Networks for Rapid Adaptation of Acoustic Models"],"prefix":"10.1109","volume":"25","author":[{"given":"Penny","family":"Karanasou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Gales","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip C.","family":"Woodland","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Eigenvoices for speaker adaptation","author":"kuhn","year":"1998","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref33","first-page":"2","article-title":"Pipelined back-propagation for context-dependent deep neural networks","author":"chen","year":"2012","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178782"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881693"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/89.848223"},{"key":"ref34","first-page":"2180","article-title":"Adaptation of deep neural network acoustic models using factorised i-vectors","author":"karanasou","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref28","first-page":"2872","article-title":"I-vector estimation using informative priors for adaptation of deep neural networks","author":"karanasou","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref27","first-page":"3037","article-title":"Modified-prior i-vector estimation for language identification of short duration utterances","author":"travadi","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref29","article-title":"Transformation smoothing for speaker and environmental adaptation","author":"gales","year":"1997","journal-title":"Proc 5th Eur Conf Speech Commun Technol"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639212"},{"key":"ref1","first-page":"1895","article-title":"A comparative analytic study on the gaussian mixture and context dependent deep neural network hidden markov models","author":"huang","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639211"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"657","DOI":"10.21437\/Interspeech.2013-188","article-title":"iVector-based acoustic data selection","author":"siohan","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref21","article-title":"Towards speaker adaptive training of deep neural network acoustic models","author":"miao","year":"2014","journal-title":"Proc INTERSPEECH"},{"article-title":"Joint factor analysis of speaker and session variability: Theory and algorithms","year":"2006","author":"kenny","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853591"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"249","DOI":"10.21437\/Interspeech.2011-53","article-title":"Analysis of i-vector length normalization in speaker recognition systems","author":"garcia-romero","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref25","article-title":"Bayesian speaker verification with heavy-tailed priors","author":"kenny","year":"2010","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960723"},{"year":"0","key":"ref51","article-title":"Generative kernels and score-spaces for classification of speech"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638951"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"441","DOI":"10.21437\/Interspeech.2011-170","article-title":"Sequential classification criteria for NNs in automatic speech recognition","author":"wang","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref52","first-page":"3581","article-title":"A general artificial neural network extension for htk","author":"zhang","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref10","article-title":"Regularized adaptation of discriminative classifiers","volume":"1","author":"li","year":"2006","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639201"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854819"},{"key":"ref12","first-page":"2171","article-title":"Speaker-adaptation for hybrid hmm-ann continuous speech recognition system","author":"neto","year":"1995","journal-title":"Proc 5th Eur Conf Speech Commun Technol"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.11.005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424251"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178785"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178787"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178829"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"ref19","first-page":"234","article-title":"Recnorm: Simultaneous normalisation and classification applied to speech recognition","author":"bridle","year":"1990","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854663"},{"key":"ref8","first-page":"3224","article-title":"Parameterised sigmoid and ReLU hidden activation functions for DNN acoustic modelling","author":"zhang","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"ref49","article-title":"The development of the Cambridge University RT-04 diarisation system","author":"tranter","year":"2004","journal-title":"Proc Rich Transcription Fall Workshop"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178783"},{"key":"ref46","first-page":"4315","article-title":"Combining i-vector representation and structured neural networks for rapid adaptation","author":"wu","year":"2015","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"959","DOI":"10.21437\/Interspeech.2012-286","article-title":"Exploring rich expressive information from audiobook data using cluster adaptive training","author":"chen","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref48","first-page":"5","article-title":"1997 broadcast news benchmark test results: English and non-english","author":"pallett","year":"1998","journal-title":"Proc DARPA Broadcast News Transcription Understanding Workshop"},{"key":"ref47","first-page":"11","article-title":"The 1996 broadcast news speech and language-model corpus","author":"graff","year":"1997","journal-title":"Proc DARPA Speech Recognit Workshop"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"2425","DOI":"10.21437\/Interspeech.2005-647","article-title":"MLLR transforms as features in speaker recognition","author":"stolcke","year":"2005","journal-title":"Proc INTERSPEECH"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0010"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"1644","DOI":"10.21437\/Interspeech.2010-475","article-title":"Prior information for rapid speaker adaptation","author":"breslin","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref43","article-title":"MLLR techniques for speaker recognition","author":"ferras","year":"2008","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7869428\/07857716.pdf?arnumber=7857716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,22]],"date-time":"2024-06-22T14:35:01Z","timestamp":1719066901000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7857716\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4]]},"references-count":57,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2670141","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2017,4]]}}}