{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T23:37:04Z","timestamp":1785800224205,"version":"3.56.0"},"reference-count":36,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639635","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T23:36:34Z","timestamp":1550187394000},"page":"250-257","source":"Crossref","is-referenced-by-count":29,"title":["A Teacher-Student Learning Approach for Unsupervised Domain Adaptation of Sequence-Trained ASR Models"],"prefix":"10.1109","author":[{"given":"Vimal","family":"Manohar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pegah","family":"Ghahremani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Povey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"The Kaldi Speech Recognition Toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref32","first-page":"3586","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"InterSpeech"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref30","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":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198793"},{"key":"ref35","article-title":"The mixer 6 corpus: Resources for cross-channel and text independent speaker recognition","author":"brandschain","year":"2010","journal-title":"Proc of LREC"},{"key":"ref34","first-page":"100","article-title":"The ami meeting corpus","volume":"88","author":"mccowan","year":"2005","journal-title":"Proc Int Conf Methods Tech Behav Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268918"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref12","first-page":"2654","article-title":"Do deep nets really need to be deep?","author":"ba","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"arXiv preprint arXiv 1503"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639201"},{"key":"ref15","article-title":"Large-scale domain adaptation via teacher-student learning","author":"li","year":"2017","journal-title":"arXiv preprint arXiv 1708 05227"},{"key":"ref16","first-page":"2761","article-title":"Sequence student-teacher training of deep neural networks","volume":"8","author":"wong","year":"2016","journal-title":"Proceedings of the Conference of the International Speech Communication Association-Interspeech"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-017-9399-z"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1475"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref28","article-title":"Reverberation robust acoustic modeling using i-vectors with time delay neural networks","author":"peddinti","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2015.7415532"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref3","first-page":"17","article-title":"Deep learning of representations for unsupervised and transfer learning","volume":"27","author":"bengio","year":"2012","journal-title":"ICML Unsupervised and Transfer Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404843"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1986.1169179"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1109\/ASRU.2017.8268947","article-title":"Investigation of Transfer Learning for LF-MMI Trained Neural Networks for ASR","author":"ghahrehmani","year":"2017","journal-title":"Automatic Speech Recognition and Understanding (ASRU) 2017 IEEE Workshop on"},{"key":"ref7","first-page":"2751","article-title":"Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI","author":"povey","year":"2016","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2015.01.010"},{"key":"ref9","article-title":"Semisupervised training of acoustic models using lattice-free mmi","author":"manohar","year":"2018","journal-title":"ICASSP"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref20","article-title":"JHU Kaldi System for Arabic MGB-3 ASR Challenge using Diarization, Audio-Transcript alignment and Transfer learning","author":"manohar","year":"2017","journal-title":"Proc ASRU 2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462619"},{"key":"ref24","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref23","first-page":"3214","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163922"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-129","article-title":"An exploration of dropout with LSTMs","author":"cheng","year":"2017","journal-title":"Proc INTERSPEECH"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","location":"Athens, Greece","start":{"date-parts":[[2018,12,18]]},"end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639635.pdf?arnumber=8639635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T02:58:49Z","timestamp":1643252329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639635\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639635","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}