{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T01:09:26Z","timestamp":1760404166531,"version":"3.37.3"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000735","name":"University of Cambridge","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000735","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1109\/taslp.2019.2929859","type":"journal-article","created":{"date-parts":[[2019,7,22]],"date-time":"2019-07-22T23:32:27Z","timestamp":1563838347000},"page":"1725-1736","source":"Crossref","is-referenced-by-count":6,"title":["General Sequence Teacher\u2013Student Learning"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3742-7510","authenticated-orcid":false,"given":"Jeremy Heng Meng","family":"Wong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5311-8219","authenticated-orcid":false,"given":"Mark John Francis","family":"Gales","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9500-081X","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266481"},{"key":"ref33","first-page":"28","article-title":"The AMI meeting corpus: A pre-announcement","author":"carletta","year":"2005","journal-title":"Proc Mach Learn Multimodal Interaction"},{"key":"ref32","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc Autom Speech Recognit Understanding Proc (ASRU)"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1109\/TASL.2007.913036","article-title":"Random forests of phonetic decision trees for acoustic modeling in conversational speech recognition","volume":"16","author":"xue","year":"2008","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref30","first-page":"105","article-title":"Minimum phone error and I-smoothing for improved discriminative training","author":"povey","year":"2002","journal-title":"Proc Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268920"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472769"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-462"},{"article-title":"MGB challenge","year":"2017","author":"bell","key":"ref34"},{"key":"ref10","first-page":"197","article-title":"Constructing ensembles of ASR systems using randomized decision trees","author":"siohan","year":"2005","journal-title":"Proc Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462353"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-145"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268918"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2323"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075885"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0190(76)90095-8"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2014.6936680"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007607513941"},{"key":"ref28","first-page":"2406","article-title":"Hypothesis spaces for minimum Bayes risk training in large vocabulary speech recognition","author":"gibson","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref4","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2014","journal-title":"Proc Neural Inf Process Syst (NIPS) Deep Learn Representation Learn Workshop"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-639"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-519"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2011.03.001"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366914"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-911"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/34.58871"},{"key":"ref2","first-page":"1910","article-title":"Learning small-size DNN with output-distribution-based criteria","author":"li","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref9","first-page":"1915","article-title":"Ensemble deep learning for speech recognition","author":"deng","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366918"},{"key":"ref22","article-title":"Weight averaging for neural networks and local resampling schemes","author":"utans","year":"1996","journal-title":"Proc Assoc Adv Artif Intell (AAAI)"},{"key":"ref21","article-title":"Combination and joint training of acoustic classifiers for speech recognition","author":"kirchhoff","year":"2000","journal-title":"Proc Automat Speech Recognition Challenges for the New Millenium"},{"key":"ref24","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref23","article-title":"Checkpoint ensembles: Ensemble methods from a single training process","author":"chen","year":"2017","journal-title":"arXiv 1710 03282"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref25","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"Proc Workshop Represent Learn Int Conf Mach Learn (ICML)"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8784423\/08768232.pdf?arnumber=8768232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:05:11Z","timestamp":1657746311000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8768232\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":38,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2929859","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2019,11]]}}}