{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T06:29:36Z","timestamp":1729664976335,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/slt.2014.7078568","type":"proceedings-article","created":{"date-parts":[[2015,4,3]],"date-time":"2015-04-03T15:03:55Z","timestamp":1428073435000},"page":"165-170","source":"Crossref","is-referenced-by-count":19,"title":["Improvements to speaker adaptive training of deep neural networks"],"prefix":"10.1109","author":[{"given":"Yajie","family":"Miao","sequence":"first","affiliation":[]},{"given":"Lu","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Florian","family":"Metze","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"1559","DOI":"10.21437\/Interspeech.2009-385","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 INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638284"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639081"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865479"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/1289189.1289244"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424213"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163922"},{"key":"ref19","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc ASRU 2011"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-10","article-title":"Application of pretrained deep neural networks to large vocabulary speech recognition","author":"jaitly","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424251"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707763"},{"key":"ref3","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":"Proc INTERSPEECH"},{"key":"ref6","first-page":"526","article-title":"Hermitian-based hidden activation functions for adaptation of hybrid HMM\/ANN models","author":"siniscalchi","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639211"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref7","article-title":"Improved feature processing for deep neural networks","author":"rath","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref9","article-title":"Towards speaker adaptive training of deep neural network acoustic models","author":"miao","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref20","article-title":"Kaldi+PDNN: building DNN-based ASR systems with Kaldi and PDNN","author":"miao","year":"2014","journal-title":"arXiv 1401 6984"},{"key":"ref22","article-title":"ALIZE\/SpkDet: a state-of-the-art open source software for speaker recognition","author":"bonastre","year":"2008","journal-title":"Proc ISCA\/IEEE Speaker"},{"key":"ref21","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":"Journal of Machine Learning Research"},{"journal-title":"Discriminative training for large vocabulary speech recognition","year":"2003","author":"povey","key":"ref24"},{"key":"ref23","first-page":"94","article-title":"Modular Combination of Deep Neural Networks for Acoustic Modeling","author":"gehring","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref26","article-title":"Improving language-universal feature extraction with deep maxout and convolutional neural networks","author":"miao","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref25","article-title":"Distributed learning of multilingual DNN feature extractors using GPUs","author":"miao","year":"2014","journal-title":"Proc INTERSPEECH"}],"event":{"name":"2014 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2014,12,7]]},"location":"South Lake Tahoe, NV, USA","end":{"date-parts":[[2014,12,10]]}},"container-title":["2014 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7066250\/7078533\/07078568.pdf?arnumber=7078568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,4]],"date-time":"2022-05-04T05:25:07Z","timestamp":1651641907000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7078568\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/slt.2014.7078568","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}