{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T03:30:00Z","timestamp":1789183800762,"version":"build-2803163510"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2016,12,1]],"date-time":"2016-12-01T00:00:00Z","timestamp":1480550400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2016,12,1]],"date-time":"2016-12-01T00:00:00Z","timestamp":1480550400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2016,12,1]],"date-time":"2016-12-01T00:00:00Z","timestamp":1480550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2016,12,1]],"date-time":"2016-12-01T00:00:00Z","timestamp":1480550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007880","name":"Johns Hopkins University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007880","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"DARPA","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004318","name":"Microsoft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004318","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Amazon"},{"DOI":"10.13039\/100014462","name":"Mitsubishi Electric Research Laboratories","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100014462","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shanghai Sailing Program","award":["16YF1405300"],"award-info":[{"award-number":["16YF1405300"]}]},{"DOI":"10.13039\/501100013285","name":"Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100013285","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61573241"],"award-info":[{"award-number":["61573241"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61603252"],"award-info":[{"award-number":["61603252"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Interdisciplinary Program (14JCZ03)"},{"DOI":"10.13039\/501100004921","name":"Shanghai Jiao Tong University in China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004921","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ICASSP"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/taslp.2016.2598308","type":"journal-article","created":{"date-parts":[[2016,8,4]],"date-time":"2016-08-04T18:11:15Z","timestamp":1470334275000},"page":"2231-2240","source":"Crossref","is-referenced-by-count":21,"title":["Neural Network Based Multi-Factor Aware Joint Training for Robust Speech Recognition"],"prefix":"10.1109","volume":"24","author":[{"given":"Yanmin","family":"Qian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"An introduction to computational networks and the computational network toolkit","author":"yu","year":"2014"},{"key":"ref38","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638962"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178782"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178844"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref37","first-page":"185","article-title":"Multi-task learning for text-dependent speaker verification","author":"chen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854673"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178923"},{"key":"ref34","first-page":"1086","article-title":"Modeling speaker variability using long short-term memory networks for speech recognition","author":"li","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205029"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178830"},{"key":"ref11","first-page":"4041","article-title":"A minimum-mean-square-error noise reduction algorithm on mel-frequency cepstra for robust speech recognition","author":"yu","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.11.008"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495581"},{"key":"ref14","first-page":"954","article-title":"An initial investigation of long-term adaptation for meeting transcription","author":"chen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854661"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707744"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178925"},{"key":"ref19","first-page":"526","article-title":"Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN\/HMM systems","author":"li","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854662"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref27","article-title":"Speech recognition in noisy environments","author":"moreno","year":"1996"},{"key":"ref3","first-page":"437","article-title":"Conversational speech transcription using context-dependent deep neural networks","author":"seide","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2163395"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.07.003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2198059"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(94)00059-J"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref9","first-page":"636","article-title":"Joint adaptation and adaptive training of TVWR for robust automatic speech recognition","author":"shilin","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472783"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.11.005"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472685"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref24","first-page":"2180","article-title":"Adaptation of deep neural network acoustic models using factorised i-vectors","author":"karanasou","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref41","article-title":"Aurora working group: DSR front end LVCSR evaluation au\/384\/02","author":"parihar","year":"0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881693"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404810"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"1713","DOI":"10.1109\/TASLP.2014.2346313","article-title":"Fast adaptation of deep neural network based on discriminant codes for speech recognition","volume":"22","author":"xue","year":"2014","journal-title":"IEEE Trans Audio Speech Lang Process"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/ieeexplore.ieee.org\/ielaam\/6570655\/7571201\/7533439-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7571201\/07533439.pdf?arnumber=7533439","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:54:23Z","timestamp":1649444063000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7533439\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":43,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2016.2598308","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,12]]}}}