{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T23:52:46Z","timestamp":1791330766163,"version":"4.3.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2016,12,1]],"date-time":"2016-12-01T00:00:00Z","timestamp":1480550400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/taslp.2016.2601146","type":"journal-article","created":{"date-parts":[[2016,8,17]],"date-time":"2016-08-17T19:23:52Z","timestamp":1471461832000},"page":"2241-2250","source":"Crossref","is-referenced-by-count":43,"title":["Factorized Hidden Layer Adaptation for Deep Neural Network Based Acoustic Modeling"],"prefix":"10.1109","volume":"24","author":[{"given":"Lahiru","family":"Samarakoon","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khe Chai","family":"Sim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472683"},{"key":"ref72","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref71","article-title":"An introduction to computational networks and the computational network toolkit","author":"yu","year":"2014"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/89.759034"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472690"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707744"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854828"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.08.005"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2014.6936583"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15760-8_54"},{"key":"ref32","article-title":"Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system","author":"neto","year":"0","journal-title":"Proc 4th Eur Conf Speech Commun Technol"},{"key":"ref31","first-page":"526","article-title":"Comparison of discriminative input and output transformation for speaker adaptation in the hybrid NN\/HMM systems","author":"li","year":"0","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc"},{"key":"ref30","first-page":"2183","article-title":"Connectionist speaker normalization and adaptation","author":"abrash","year":"0","journal-title":"Proc Euro speech"},{"key":"ref37","first-page":"2365","article-title":"Restructuring of deep neural network acoustic models with singular value decomposition.","author":"xue","year":"0","journal-title":"Proc Conf Int Speech Commun Assoc"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660239"},{"key":"ref34","first-page":"2574","article-title":"A initial attempt on task-specific adaptation for deep neural network-based large vocabulary continuous speech recognition","author":"xiao","year":"0","journal-title":"Proc Conf Int Speech Commun Assoc"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472631"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404787"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853591"},{"key":"ref63","first-page":"4610","article-title":"An investigation of augmenting speaker representations to improve speaker normalization for DNN-based speech recognition","author":"huang","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref28","article-title":"Learning representations by back-propagating errors","volume":"5","author":"rumelhart","year":"1988","journal-title":"Cognitive Modeling"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472634"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-007-9040-x"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639014"},{"key":"ref66","first-page":"2180","article-title":"Adaptation of deep neural network acoustic models using factorised i-vectors","author":"karanasou","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref29","article-title":"Online learning and stochastic approximations","volume":"17","author":"bottou","year":"1998","journal-title":"On-Line Learning on Neural Networks"},{"key":"ref67","first-page":"2872","article-title":"I-vector estimation using informative priors for adaptation of deep neural networks","author":"karanasou","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref68","first-page":"2877","article-title":"Robust i-vector based adaptation of DNN acoustic model for speech recognition","author":"garimella","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref69","first-page":"2854","article-title":"Robust i-vector extraction for neural network adaptation in noisy environment","author":"yu","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2285487"},{"key":"ref22","first-page":"4325","article-title":"Cluster adaptive training for deep neural network","author":"tian","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853585"},{"key":"ref24","first-page":"553","article-title":"Performance analysis of the Aurora large vocabulary baseline system","author":"parihar","year":"0","journal-title":"Proc Eur Signal Proc Conf"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178785"},{"key":"ref26","article-title":"The AMI meeting corpus","volume":"88","author":"mccowan","year":"0","journal-title":"Proc Int Conf Methods Tech Behav Res"},{"key":"ref25","first-page":"161","article-title":"Improved performance of Aurora-4 using HTK and unsupervised MLLR adaptation","author":"yeung","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref50","first-page":"1081","article-title":"Regularized sequence-level deep neural network model adaptation","author":"huang","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref51","first-page":"i","article-title":"Regularized adaptation of discriminative classifiers","volume":"1","author":"li","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref59","article-title":"Factorized deep neural networks for adaptive speech recognition","author":"yu","year":"0","journal-title":"Proc IEEE Int Workshop Statistical Mach Learning Speech Process"},{"key":"ref58","doi-asserted-by":"crossref","first-page":"1713","DOI":"10.1109\/TASLP.2014.2346313","article-title":"Fast adaptation of deep neural network based on discriminant codes for speech recognition","volume":"22","author":"xue","year":"2014","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2457612"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758061"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541105"},{"key":"ref54","first-page":"3605","article-title":"Structured output layer with auxiliary targets for context-dependent acoustic modelling","author":"swietojanski","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078566"},{"key":"ref52","first-page":"3625","article-title":"Rapid adaptation for deep neural networks through multi-task learning","author":"huang","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/89.848223"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639201"},{"key":"ref40","first-page":"1091","article-title":"Intermediate-layer DNN adaptation for offline and session-based iterative speaker adaptation","author":"kumar","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854823"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639211"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-5779-3","author":"yu","year":"2015","journal-title":"Automatic Speech Recognition?A Deep Learning Approach"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115720"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639014"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854663"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/89.279278"},{"key":"ref5","first-page":"2578","article-title":"Application of pretrained deep neural networks to large vocabulary speech recognition","author":"jaitly","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0010"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2270370"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607807"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639212"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415279"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424251"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472684"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472630"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862102"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178783"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7571201\/07546852.pdf?arnumber=7546852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T18:57:01Z","timestamp":1749063421000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7546852\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":76,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2016.2601146","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,12]]}}}