{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T16:31:33Z","timestamp":1772037093729,"version":"3.50.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2016,4,1]],"date-time":"2016-04-01T00:00:00Z","timestamp":1459468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["IIS-1409431"],"award-info":[{"award-number":["IIS-1409431"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"AFOSR","doi-asserted-by":"publisher","award":["FA9550-12-1-0130"],"award-info":[{"award-number":["FA9550-12-1-0130"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ohio Supercomputer Center"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2016,4]]},"DOI":"10.1109\/taslp.2016.2528171","type":"journal-article","created":{"date-parts":[[2016,2,10]],"date-time":"2016-02-10T19:26:48Z","timestamp":1455132408000},"page":"796-806","source":"Crossref","is-referenced-by-count":108,"title":["A Joint Training Framework for Robust Automatic Speech Recognition"],"prefix":"10.1109","volume":"24","author":[{"given":"Zhong-Qiu","family":"Wang","sequence":"first","affiliation":[]},{"given":"DeLiang","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref33","first-page":"3214","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2372314"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854051"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.08.005"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707746"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078567"},{"key":"ref34","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop Autom Speech Recog and Understanding"},{"key":"ref28","first-page":"2430","article-title":"A study on deep neural network acoustic model adaptation for robust far-field speech recognition","author":"mirsamadi","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178795"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2305833"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2359159"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404836"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288820"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2329237"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1121\/1.408546"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref25","first-page":"358","article-title":"A long, deep and wide artificial neural net for robust speech recognition in unknown noise","author":"li","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref50","first-page":"2839","article-title":"Joint training of speech separation, filterbank and acoustic model for robust automatic speech recognition","author":"wang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref51","article-title":"Phoneme-specific speech separation","author":"wang","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639201"},{"key":"ref57","article-title":"Feature learning in deep neural networks—Studies on speech recognition tasks","author":"yu","year":"2013"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","article-title":"A regression approach to speech enhancement based on deep neural networks","volume":"23","author":"xu","year":"2015","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2014.7032183"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854661"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2318514"},{"key":"ref11","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref40","article-title":"Robustness is dead! Long live robustness!","author":"seltzer","year":"0","journal-title":"Proc REVERB Challenge Workshop"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref13","first-page":"2484","article-title":"Deep neural network based spectral feature mapping for robust speech recognition","author":"han","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2416653"},{"key":"ref15","article-title":"Deepspeech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1121\/1.4820893"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/89.326616"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2008.11.001"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref4","first-page":"2992","article-title":"Is speech enhancement pre-processing still relevant when using deep neural networks for acoustic modeling?","author":"delcroix","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref3","first-page":"3274","article-title":"Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks","author":"chen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref6","first-page":"616","article-title":"Robust speech recognition with speech enhanced deep neural networks","author":"du","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288333"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref7","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178797"},{"key":"ref46","article-title":"Deep neural network based supervised speech segregation generalizes to novel noises through large-scale training","author":"wang","year":"2015"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/9780470043387"},{"key":"ref48","first-page":"2469","article-title":"Time-frequency masking for large scale robust speech recognition","author":"wang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2221459"},{"key":"ref42","first-page":"2345","article-title":"Sequence-discriminative training of deep neural networks","author":"vesel\u00fd","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-22794-6_12"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707723"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7422174\/7403942.pdf?arnumber=7403942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:02:26Z","timestamp":1642003346000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7403942\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,4]]},"references-count":58,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2016.2528171","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,4]]}}}