{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T21:40:08Z","timestamp":1750369208125,"version":"3.41.0"},"reference-count":38,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/icassp.2017.7953146","type":"proceedings-article","created":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T21:35:36Z","timestamp":1497994536000},"page":"5190-5194","source":"Crossref","is-referenced-by-count":0,"title":["Effective joint training of denoising feature space transforms and Neural Network based acoustic models"],"prefix":"10.1109","author":[{"given":"Takashi","family":"Fukuda","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Osamu","family":"Ichikawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gakuto","family":"Kurata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryuki","family":"Tachibana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel","family":"Thomas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1233"},{"article-title":"Improving neural networks by preventing coadaptation of feature detectors","year":"2012","author":"hinton","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472698"},{"key":"ref31","article-title":"Aurora Working Group: DSP Front-end and LVCSR Evaluation AU\/384\/02","author":"parihar","year":"2002","journal-title":"Institute for Signal and Information Processing Mississippi State University"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178797"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1161"},{"key":"ref36","article-title":"Multi-task joint-learning of deep neural networkds for robust speech recognition","author":"qian","year":"2015","journal-title":"ASRU"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078567"},{"key":"ref34","first-page":"37","article-title":"Using missing feature theory to actively select features for robust speech recognition with interruptions, filtering and noise","volume":"97","author":"lippmann","year":"1997","journal-title":"Eurospeech"},{"key":"ref10","first-page":"556","article-title":"Algorithms for non-negative matrix factorization","author":"lee","year":"0","journal-title":"Advances in Neural Information Processing Systems 2001"},{"key":"ref11","first-page":"17","article-title":"Evaluation of a noise-robust DSR front-end on Aurora databases","author":"macho","year":"2002","journal-title":"ICSLP"},{"key":"ref12","first-page":"4041","article-title":"A minimum-mean-square-error noise reduction algorithm on Melfrequency cepstra for robust speech recognition","author":"yu","year":"2008","journal-title":"Proc IEEE Acoustics Speech Signal Processing (ICASSP)"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"3002","DOI":"10.21437\/Interspeech.2013-278","article-title":"An investigation of spectral restoration algorithms for deep neural networks based noise robust speech recognition","author":"li","year":"2013","journal-title":"InterSpeech"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"2992","DOI":"10.21437\/Interspeech.2013-276","article-title":"Is speech enhancement pre-processing still relevant when using deep neural networks for acoustic modeling?","author":"delcroix","year":"2013","journal-title":"InterSpeech"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424251"},{"key":"ref17","article-title":"Investigation of parametric rectified linear units for noise robust speech recognition","author":"sivadas","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref18","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","volume":"2015","author":"peddinti","year":"0","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-388"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2015-632","article-title":"The IBM 2015 English conversational telephone speech recognition system","author":"saon","year":"2015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404841"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854669"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288824"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854051"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960461"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288820"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495668"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"437","DOI":"10.21437\/Interspeech.2011-169","article-title":"Conversational speech transcription using context-dependent deep neural networks","author":"seide","year":"2011","journal-title":"InterSpeech"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163900"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"ref22","first-page":"22","article-title":"Recurrent neural networks for noise reduction in robust asr","author":"maas","year":"2012","journal-title":"InterSpeech"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639211"},{"key":"ref24","article-title":"Robust speech recognition using long short-term memory recurrent neural networks for hybrid acoustic modeling","volume":"2014","author":"geige","year":"0","journal-title":"InterSpeech"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472775"},{"key":"ref26","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":"The Journal of Machine Learning Research"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472780"}],"event":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2017,3,5]]},"location":"New Orleans, LA","end":{"date-parts":[[2017,3,9]]}},"container-title":["2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7943262\/7951776\/07953146.pdf?arnumber=7953146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T20:58:36Z","timestamp":1750366716000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7953146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp.2017.7953146","relation":{},"subject":[],"published":{"date-parts":[[2017,3]]}}}