{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T11:40:02Z","timestamp":1748778002531,"version":"3.41.0"},"reference-count":51,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1109\/asru.2015.7404850","type":"proceedings-article","created":{"date-parts":[[2016,2,12]],"date-time":"2016-02-12T13:55:42Z","timestamp":1455285342000},"page":"596-603","source":"Crossref","is-referenced-by-count":7,"title":["Speaker adaptive joint training of Gaussian mixture models and bottleneck features"],"prefix":"10.1109","author":[{"given":"Zoltan","family":"Tuske","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pavel","family":"Golik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ralf","family":"Schluter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hermann","family":"Ney","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"A Log-Linear Discriminative Modeling Framework for Speech Recognition","year":"2010","author":"heigold","key":"ref39"},{"key":"ref38","first-page":"897","article-title":"Multiplicative updates for classification by mixture models","volume":"2","author":"saul","year":"2001","journal-title":"NIPS"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"2189","DOI":"10.21437\/Interspeech.2014-490","article-title":"Towards Speaker Adaptive Training of Deep Neural Network Acoustic Models","author":"miao","year":"2014","journal-title":"InterSpeech"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639211"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854826"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178779"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178776"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"89","DOI":"10.21437\/Interspeech.2013-44","article-title":"Lattice-based training of bottleneck feature extraction neural networks","author":"paulik","year":"2013","journal-title":"InterSpeech"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639013"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854679"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639209"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.21437\/Interspeech.2014-308","article-title":"Asynchronous Stochastic Optimization for Sequence Training of Deep Neural Networks: Towards Big Data","author":"mcdermott","year":"2014","journal-title":"InterSpeech"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854669"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"2171","DOI":"10.21437\/Eurospeech.1995-411","article-title":"Speaker-Adaptation for Hybrid HMM-ANN Continuous Speech Recognition System","author":"neto","year":"1995","journal-title":"Eurospeech"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639201"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.11.005"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"2183","DOI":"10.21437\/Eurospeech.1995-414","article-title":"Connectionist speaker normalization and adaptation","author":"abrash","year":"1995","journal-title":"Eurospeech"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854828"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163900"},{"key":"ref25","first-page":"24","article-title":"Feature engineering in context-dependent deep neural networks for conversational speech transcription","author":"seide","year":"2011","journal-title":"ASRU"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366996"},{"key":"ref51","first-page":"-105i","article-title":"Minimum phone error and i-smoothing for improved discriminative training","author":"povey","year":"2002","journal-title":"ICASSP"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/89.279278"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415284"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"921","DOI":"10.21437\/Interspeech.2004-337","article-title":"On using MLP features in LVCSR","author":"zhu","year":"2004","journal-title":"InterSpeech"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"306","DOI":"10.21437\/Interspeech.2010-117","article-title":"Analysis of Gender Normalization Using MLP and VTLN Features","author":"schaaf","year":"2010","journal-title":"InterSpeech"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"1089","DOI":"10.21437\/Interspeech.2011-413","article-title":"A study on speaker normalized MLP features in LVCSR","author":"t\u00fcske","year":"2011","journal-title":"InterSpeech"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1895","DOI":"10.21437\/Interspeech.2014-429","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":"InterSpeech"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639212"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"2199","DOI":"10.21437\/Interspeech.2014-492","article-title":"Speaker Dependent Bottleneck Layer Training for Speaker Adaptation in Automatic Speech Recognition","author":"doddipatla","year":"2014","journal-title":"InterSpeech"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.550603"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"526","DOI":"10.21437\/Interspeech.2010-214","article-title":"Comparison of Discriminative Input and Output Transformations for Speaker Adaptation in the Hybrid NN\/HMM Systems","author":"li","year":"2010","journal-title":"InterSpeech"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541101"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"104","DOI":"10.21437\/Interspeech.2013-47","article-title":"A Scalable Approach to Using DNN-Derived Features in GMM-HMM Based Acoustic Modeling For LVCSR","author":"yan","year":"2013","journal-title":"InterSpeech"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0010"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1445","DOI":"10.21437\/Eurospeech.2003-422","article-title":"Vocal tract normalization as linear transformation of MFCC","author":"pitz","year":"2003","journal-title":"Eurospeech"},{"key":"ref49","first-page":"315","article-title":"Deep Sparse Rectifier Neural Networks","author":"glorot","year":"2011","journal-title":"AISTATS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/89.466659"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.803435"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946920"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"890","DOI":"10.21437\/Interspeech.2014-223","article-title":"Acoustic Modeling with Deep Neural Networks Using Raw Time Signal for LVCSR","author":"t\u00fcske","year":"2014","journal-title":"InterSpeech"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853582"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"1517","DOI":"10.21437\/Interspeech.2010-443","article-title":"The RWTH 2009 QUAERO ASR evaluation system for English and German","author":"nu\u00dfbaum-thom","year":"2010","journal-title":"InterSpeech"},{"key":"ref41","article-title":"Factorized deep neural networks for adaptive speech recognition","author":"yu","year":"2012","journal-title":"Proc Int Workshop Statist Mach Learn Speech Process"},{"key":"ref44","article-title":"RASR - The RWTH Aachen University Open Source Speech Recognition Toolkit","author":"rybach","year":"2011","journal-title":"ASRU"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"1477","DOI":"10.21437\/Interspeech.2013-383","article-title":"An open-source state-of-the-art toolbox for broadcast news diarization","author":"rouvier","year":"2013","journal-title":"InterSpeech"}],"event":{"name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","start":{"date-parts":[[2015,12,13]]},"location":"Scottsdale, AZ","end":{"date-parts":[[2015,12,17]]}},"container-title":["2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7397480\/7404758\/07404850.pdf?arnumber=7404850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T10:58:03Z","timestamp":1748775483000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7404850\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/asru.2015.7404850","relation":{},"subject":[],"published":{"date-parts":[[2015,12]]}}}