{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:16:59Z","timestamp":1772756219162,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1109\/asru.2015.7404842","type":"proceedings-article","created":{"date-parts":[[2016,2,12]],"date-time":"2016-02-12T13:55:42Z","timestamp":1455285342000},"page":"539-546","source":"Crossref","is-referenced-by-count":50,"title":["JHU ASpIRE system: Robust LVCSR with TDNNS, iVector adaptation and RNN-LMS"],"prefix":"10.1109","author":[{"given":"Vijayaditya","family":"Peddinti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoguo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vimal","family":"Manohar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"Ko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Povey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163930"},{"key":"ref32","first-page":"196","article-title":"Rnnlm-recurrent neural network language modeling toolkit","author":"mikolov","year":"2011","journal-title":"Proc of the 2011 ASRU Workshop"},{"key":"ref31","article-title":"Lib-rispeech: an ASR corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"Proceedings of the International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref30","article-title":"SRILM - an extensible language modeling toolkit","author":"stolcke","year":"2002","journal-title":"Proceedings of Interspeech"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854535"},{"key":"ref34","article-title":"Learning internal representations by error propagation","author":"rumelhart","year":"1985","journal-title":"DTIC Document Tech Rep"},{"key":"ref10","article-title":"Parallel training of Deep Neural Networks with Natural Gradient and Parameter Averaging","author":"povey","year":"2015","journal-title":"Proc ICLR Workshop"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref13","article-title":"Reverberation robust acoustic modeling using i-vectors with time delay neural networks","author":"peddinti","year":"2015","journal-title":"Proceedings of Interspeech"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853589"},{"key":"ref15","article-title":"Acoustical sound database in real environments for sound scene understanding and hands-free speech recognition","author":"nakamura","year":"2000","journal-title":"LREC"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701894"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2009.5201259"},{"key":"ref18","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"Proceedings of Interspeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.08.008"},{"key":"ref28","article-title":"The CU-HTK march 2000 Hub5e transcription system","volume":"1","author":"hain","year":"2000","journal-title":"Proceedings of Speech Transcription Workshop"},{"key":"ref4","first-page":"1","article-title":"Fast Adaptation of Deep Neural Network based on Discriminant Codes for Speech Recognition","volume":"pp","author":"xue","year":"2014","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758060"},{"key":"ref3","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"Proceedings of Interspeech"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref29","article-title":"Automatic learning of word pronunciation from data","author":"fosler","year":"1996","journal-title":"Proceedings of the International Conference on Spoken Language Processing"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163922"},{"key":"ref8","year":"2015","journal-title":"Automatic Speech recognition In Reverberant Environments (ASpIRE) Challenge"},{"key":"ref7","article-title":"Use of multiple front-ends and i-vector-based speaker adaptation for robust speech recognition","author":"alam","year":"2014","journal-title":"Proc of IEEE REVERB Workshop"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref9","first-page":"69","article-title":"The fisher corpus: a resource for the next generations of speech-to-text","volume":"4","author":"cieri","year":"2004","journal-title":"LREC"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205029"},{"key":"ref20","article-title":"Minimum bayes risk acoustic model estimation and adaptation","author":"gibson","year":"2008"},{"key":"ref22","article-title":"Semi-supervised maximum mutual information training of deep neural network acoustic models","author":"manohar","year":"2015","journal-title":"Proceedings of Interspeech"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"2345","DOI":"10.21437\/Interspeech.2013-548","article-title":"Sequence-discriminative training of deep neural networks","author":"vesel?","year":"2013","journal-title":"Proceedings of Interspeech"},{"key":"ref24","article-title":"Dual system combination approach for various reverberant environments with dereverberation techniques","author":"tachioka","year":"2014","journal-title":"Proc of IEEE RE-VERB Workshop"},{"key":"ref23","article-title":"Linear prediction-based dereverberation with advanced speech enhancement and recognition technologies for the reverb challenge","author":"delcroix","year":"2014","journal-title":"Proc of IEEE REVERB Workshop"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.03.008"},{"key":"ref25","article-title":"Pronunciation and silence probability modeling for ASR","author":"chen","year":"2015","journal-title":"Proceedings of Interspeech"}],"event":{"name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","location":"Scottsdale, AZ, USA","start":{"date-parts":[[2015,12,13]]},"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\/07404842.pdf?arnumber=7404842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T09:47:17Z","timestamp":1718358437000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7404842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/asru.2015.7404842","relation":{},"subject":[],"published":{"date-parts":[[2015,12]]}}}