{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:05:53Z","timestamp":1778083553777,"version":"3.51.4"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2015,11,1]],"date-time":"2015-11-01T00:00:00Z","timestamp":1446336000000},"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":[[2015,11]]},"DOI":"10.1109\/taslp.2015.2457612","type":"journal-article","created":{"date-parts":[[2015,7,16]],"date-time":"2015-07-16T19:01:02Z","timestamp":1437073262000},"page":"1938-1949","source":"Crossref","is-referenced-by-count":67,"title":["Speaker Adaptive Training of Deep Neural Network Acoustic Models Using I-Vectors"],"prefix":"10.1109","volume":"23","author":[{"given":"Yajie","family":"Miao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Metze","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Adaptation of deep neural network acoustic models using factorised i-vectors","author":"karanasou","year":"2014","journal-title":"Proc 15th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854823"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078568"},{"key":"ref31","article-title":"Towards speaker adaptive training of deep neural network acoustic models","author":"miao","year":"2014","journal-title":"Proc 15th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref30","article-title":"On speaker adaptation of long short-term memory recurrent neural networks","author":"miao","year":"2015","journal-title":"Proc 16th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854828"},{"key":"ref36","article-title":"Improving language-universal feature extraction with deep maxout and convolutional neural networks","author":"miao","year":"2014","journal-title":"Proc 15th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707763"},{"key":"ref34","first-page":"315","article-title":"Deep sparse rectifier networks","volume":"15","author":"glorot","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist JMLR W&CP Vol"},{"key":"ref28","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Proc 15th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref29","article-title":"Sequence discriminative distributed training of long short-term memory recurrent neural networks","author":"sak","year":"2014","journal-title":"Proc 15th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref20","first-page":"1559","article-title":"Support vector machines versus fast scoring in the low-dimensional total variability space for speaker verification","author":"dehak","year":"2009","journal-title":"Proc 10th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854669"},{"key":"ref26","article-title":"Recurrent neural networks for noise reduction in robust ASR","author":"maas","year":"2012","journal-title":"Proc 13th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.08.005"},{"key":"ref50","author":"povey","year":"2005","journal-title":"Discriminative training for large vocabulary speech recognition"},{"key":"ref51","article-title":"Kaldi+PDNN: Building DNN-based ASR systems with Kaldi and PDNN","author":"miao","year":"2014","journal-title":"arXiv preprint arXiv 1401 6984"},{"key":"ref56","article-title":"Modular combination of deep neural networks for acoustic modeling","author":"gehring","year":"2013","journal-title":"Proc 14th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638284"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853887"},{"key":"ref53","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1007\/978-3-642-35289-8_32","author":"hinton","year":"2012","journal-title":"Neural Networks Tricks of the Trade"},{"key":"ref52","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref10","article-title":"Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN\/HMM systems","author":"li","year":"2010","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424251"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854662"},{"key":"ref12","first-page":"109","article-title":"Improved feature processing for deep neural networks","author":"rath","year":"2013","journal-title":"Proc 14th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607807"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596119"},{"key":"ref16","article-title":"On speaker adaptive training of artificial neural networks","author":"trmal","year":"2010","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853591"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854826"},{"key":"ref4","article-title":"Application of pretrained deep neural networks to large vocabulary speech recognition","author":"jaitly","year":"2012","journal-title":"Proc 13th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0010"},{"key":"ref5","article-title":"Feature learning in deep neural networks-studies on speech recognition tasks","author":"yu","year":"2013","journal-title":"arXiv preprint arXiv 1301 3605"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref49","first-page":"1","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop Autom Speech Recogn Understand (ASRU)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639201"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.925147"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2270370"},{"key":"ref48","first-page":"125","article-title":"TED-LIUM: An automatic speech recognition dedicated corpus","author":"rousseau","year":"2012","journal-title":"Proc LREC"},{"key":"ref47","first-page":"152","article-title":"iVector-based discriminative adaptation for automatic speech recognition","author":"karafi\ufffdt","year":"2011","journal-title":"Proc IEEE Workshop Autom Speech Recogn Understand (ASRU)"},{"key":"ref42","first-page":"1248","article-title":"Rapid and effective speaker adaptation of convolutional neural network based models for speech recognition","author":"abdel-hamid","year":"2013","journal-title":"Proc 14th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639211"},{"key":"ref44","article-title":"Feature space maximum a posteriori linear regression for adaptation of deep neural networks","author":"huang","year":"2014","journal-title":"Proc 15th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078566"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7140863\/07160703.pdf?arnumber=7160703","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:51:39Z","timestamp":1642006299000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7160703\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,11]]},"references-count":56,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2015.2457612","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,11]]}}}