{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T15:54:51Z","timestamp":1778946891562,"version":"3.51.4"},"reference-count":37,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/icassp.2017.7953073","type":"proceedings-article","created":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T21:35:36Z","timestamp":1497994536000},"page":"4825-4829","source":"Crossref","is-referenced-by-count":21,"title":["Knowledge distillation across ensembles of multilingual models for low-resource languages"],"prefix":"10.1109","author":[{"given":"Jia","family":"Cui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Kingsbury","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Saon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"Sercu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kartik","family":"Audhkhasi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav","family":"Sethy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Markus","family":"Nussbaum-Thom","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Rosenberg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163900"},{"key":"ref32","article-title":"Scalable minimum bayes risk training of deep neural network acoustic models using distributed hessian-free optimization","author":"brian","year":"2012","journal-title":"InterSpeech"},{"key":"ref31","article-title":"Deep learning via hessian-free optimization","author":"martens","year":"0","journal-title":"ICML 2010"},{"key":"ref30","article-title":"Greedy layer-wise training of deep networks","author":"bengio","year":"0","journal-title":"Advances in Neural Information Processing Systems 2007"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref36","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"I CML"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1033"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472620"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-911"},{"key":"ref11","article-title":"Recurrent neural network training with dark knowledge transfer","author":"wang","year":"0","journal-title":"CSLT TECHNICAL REPORT-20150013 2015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref14","article-title":"Deep neural networks for acoustic modeling in speech recognition","author":"hinton","year":"0","journal-title":"IEEE Signal Processing Magazine 2012"},{"key":"ref15","article-title":"The spoken term detection (std) 2006 evaluation plan","author":"fiscus","year":"0","journal-title":"NIST USA Sep 2006"},{"key":"ref16","author":"harper","year":"0"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2013-523","article-title":"Multilin-gual hierarchical MRASTA features for ASR","author":"tuske","year":"2013","journal-title":"InterSpeech"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855129"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707719"},{"key":"ref28","article-title":"But 2014 babel system: Analysis of adaptation in nn based systems","author":"martin","year":"2014","journal-title":"InterSpeech"},{"key":"ref4","article-title":"Distilling the knowledge in a neural network","author":"dean","year":"0","journal-title":"arXiv 1503 02531v1 2015"},{"key":"ref27","article-title":"Inves-tigation into bottle-neck features for meeting speech recognition","author":"grezl","year":"2009","journal-title":"InterSpeech"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2014-432","article-title":"Learning small-size dnn with output-distribution-based criteria","author":"li","year":"2014","journal-title":"InterSpeech"},{"key":"ref6","article-title":"Blending lstms into cnns","author":"geras","year":"2016","journal-title":"ICLR Workshop"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2010.5700829"},{"key":"ref5","article-title":"Transferring knowledge from a rnn to a dnn","author":"chan","year":"0","journal-title":"Proceedings of Interspeech 2015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1190"},{"key":"ref7","article-title":"A diversity-penalizing ensemble training method for deep learning","author":"zhang","year":"0","journal-title":"Proceedings of Interspeech 2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472809"},{"key":"ref1","first-page":"2654","article-title":"Do deep nets really need to be deep?","volume":"27","author":"ba","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Speech recognition and keyword spotting for low resource languages: Babel project researchat CUED","author":"gales","year":"0","journal-title":"Spoken Language Technologies for Under-Resource Languages 2014"},{"key":"ref22","article-title":"Multilingual representations for low resource speech recognition and keyword search","author":"cui","year":"2015","journal-title":"ASRU"},{"key":"ref21","article-title":"Combination of multilingual and semi-supervised training for under-resourced languages","author":"gr\u00e9zl","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref24","first-page":"369","article-title":"Con-nectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks","author":"graves","year":"2006","journal-title":"ICML 2006"},{"key":"ref23","article-title":"Convolutional networks for images, speech, and time-series","author":"lecun","year":"0","journal-title":"The handbook of brain theory and neural networks 1995"},{"key":"ref26","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"}],"event":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"New Orleans, LA","start":{"date-parts":[[2017,3,5]]},"end":{"date-parts":[[2017,3,9]]}},"container-title":["2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7943262\/7951776\/07953073.pdf?arnumber=7953073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T21:00:15Z","timestamp":1750366815000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7953073\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp.2017.7953073","relation":{},"subject":[],"published":{"date-parts":[[2017,3]]}}}