{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T09:23:28Z","timestamp":1762507408024,"version":"3.37.3"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2018,8,1]],"date-time":"2018-08-01T00:00:00Z","timestamp":1533081600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"China NSFC projects","award":["U1736202","61603252"],"award-info":[{"award-number":["U1736202","61603252"]}]},{"name":"Shanghai Sailing Program","award":["16YF1405300"],"award-info":[{"award-number":["16YF1405300"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1109\/taslp.2018.2825432","type":"journal-article","created":{"date-parts":[[2018,4,12]],"date-time":"2018-04-12T20:27:02Z","timestamp":1523564822000},"page":"1393-1405","source":"Crossref","is-referenced-by-count":50,"title":["Adaptive Very Deep Convolutional Residual Network for Noise Robust Speech Recognition"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4723-0044","authenticated-orcid":false,"given":"Tian","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0314-3790","authenticated-orcid":false,"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hu","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4082-7497","authenticated-orcid":false,"given":"Ying","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4308-4182","authenticated-orcid":false,"given":"Wen","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7102-9826","authenticated-orcid":false,"given":"Kai","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"70","article-title":"The SJTU CHIME-4 System: Acoustic noise robustness for real single or multiple microphone\n scenarios","author":"qian","year":"0","journal-title":"The 4th CHiME speech separation and recognition challenge"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846307"},{"key":"ref33","first-page":"1478","article-title":"Convolutional neural networks for small-footprint keyword spotting","author":"sainath","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178829"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178785"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178787"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2602884"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472620"},{"key":"ref35","first-page":"3259","article-title":"Very deep convolutional neural\n networks for LVCSR","author":"bi","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref62","first-page":"338","article-title":"Long short-term memory\n recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"0","journal-title":"Proc INTERSPEECH"},{"article-title":"An introduction to computational networks and the\n computational network toolkit","year":"2014","author":"yu","key":"ref61"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2598308"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472634"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178782"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2457612"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854824"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639211"},{"key":"ref26","first-page":"5280","article-title":"Speaker-aware training of LSTM-RNNS for acoustic modeling","author":"tan","year":"2016","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178844"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2511922"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2601146"},{"key":"ref59","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707744"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472671"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref55","article-title":"Aurora working Group: DSR front end LVCSR evaluation AU\/384\/02","author":"pearce","year":"2002","journal-title":"Inst Signal Inf Process"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-203"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472630"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854828"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(94)00059-J"},{"key":"ref11","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":"ref40","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","first-page":"4041","article-title":"A\n 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":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.11.008"},{"key":"ref14","first-page":"954","article-title":"An initial investigation of long-term\n adaptation for meeting transcription","author":"chen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref15","first-page":"526","article-title":"Comparison of discriminative input and output transformations for speaker adaptation in the hybrid\n NN\/HMM Systems","author":"li","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424251"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2560534"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854826"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref3","first-page":"437","article-title":"Conversational\n 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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2198059"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178828"},{"key":"ref7","first-page":"1895","article-title":"A comparative analytic study on the\n Gaussian mixture and context dependent deep neural network hidden Markov models","author":"huang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-405"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953077"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.08.005"},{"key":"ref42","first-page":"3140","article-title":"The IBM 2015 english conversational\n telephone speech recognition system","author":"saon","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953159"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-251"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8356719\/08336909.pdf?arnumber=8336909","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:18:06Z","timestamp":1642004286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8336909\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8]]},"references-count":63,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2825432","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2018,8]]}}}