{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:21Z","timestamp":1760245041640,"version":"3.28.0"},"reference-count":55,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1109\/asru.2015.7404856","type":"proceedings-article","created":{"date-parts":[[2016,2,12]],"date-time":"2016-02-12T08:55:42Z","timestamp":1455267342000},"page":"639-646","source":"Crossref","is-referenced-by-count":15,"title":["Cambridge university transcription systems for the multi-genre broadcast challenge"],"prefix":"10.1109","author":[{"given":"P. C.","family":"Woodland","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"X.","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Y.","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M. J. F.","family":"Gales","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P.","family":"Karanasou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P.","family":"Lanchantin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"L.","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Feature engineering in context-dependent deep neural networks","author":"seide","year":"2011","journal-title":"Proc ASRU Workshop"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref33","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU Workshop"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP.2002.1005687","article-title":"Minimum phone error and I-smoothing for improved discriminative training","author":"povey","year":"2002","journal-title":"Proc ICASSP"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707746"},{"key":"ref36","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-560","article-title":"On generating Combilex pronunciations via morphological analysis","author":"richmond","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-405","article-title":"Robust LTS rules with the Combilex speech technology lexicon","author":"richmond","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref28","article-title":"The Cambridge University 2014 BOLT conversational telephone Mandarin Chinese LVCSR system for speech translation","author":"liu","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854535"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2000.0152"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288864"},{"year":"0","key":"ref1"},{"key":"ref20","article-title":"I-vector estimation using informative priors for adaptation of deep neural networks","author":"karanasou","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404859"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0186"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707719"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198734"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404857"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2011.03.001"},{"journal-title":"The HTK Book (for HTK Version 3 4)","year":"2006","author":"young","key":"ref51"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178784"},{"key":"ref54","article-title":"Parameterised sigmoid and ReLU hidden activation functions for DNN acoustic modelling","author":"zhang","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref53","article-title":"A general artificial neural network extension for HTK","author":"zhang","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-5779-3_10"},{"key":"ref10","article-title":"Recurrent Neural Network Language Model Adaptation for Multi-Genre Broadcast Speech Recognition","author":"chen","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref11","article-title":"Posterior probability decoding, confidence estimation and system combination","author":"evermann","year":"2000","journal-title":"Proc Speech Transcription Workshop"},{"key":"ref40","article-title":"Prefix tree based n-best list re-scoring for recurrent neural network language model used in speech recognition system","author":"si","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1006\/csla.1998.0043","article-title":"Maximum likelihood linear transformations for HMM-based speech recognition","volume":"12","author":"gales","year":"1997","journal-title":"Computer Speech and Langauge"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/89.759034"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878264"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(01)00061-9"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854049"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518713"},{"key":"ref19","article-title":"A Practical Guide to Training Restricted Boltzmann Machines","author":"hinton","year":"2010","journal-title":"Tech Rep UTML TR 2010-003"},{"key":"ref4","article-title":"The MGB challenge: Evaluating multi-genre broadcast media transcription","author":"bell","year":"2015","journal-title":"Proc ASRU Workshop"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607807"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.01.002"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326091"},{"key":"ref7","first-page":"99","article-title":"Latent Dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(01)00059-0"},{"key":"ref9","article-title":"Efficient GPU-based training of recurrent neural network language models using spliced sentence bunch","author":"chen","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178783"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"ref48","article-title":"Sequence-discriminative training of deep neural networks","author":"vesel?","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163903"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2270370"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2005-650","article-title":"The Cambridge University March 2005 speaker diarisation system","author":"sinha","year":"2005","journal-title":"Proc INTERSPEECH"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638967"},{"key":"ref43","article-title":"SRILM: an extensible language modeling toolkit","author":"stolcke","year":"2002","journal-title":"Proc ICSLP"}],"event":{"name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","start":{"date-parts":[[2015,12,13]]},"location":"Scottsdale, AZ, USA","end":{"date-parts":[[2015,12,17]]}},"container-title":["2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7397480\/7404758\/07404856.pdf?arnumber=7404856","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,3]],"date-time":"2022-06-03T21:23:57Z","timestamp":1654291437000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7404856\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/asru.2015.7404856","relation":{},"subject":[],"published":{"date-parts":[[2015,12]]}}}