Toshiba Cambridge Speech Group / Cambridge Research Laboratory / Baseline Acoustic Systems / Toshiba Research Europe Ltd / UK 2 Toshiba Research Europe Ltd / / /
Facility
University of Cambridge / Philip N Garner / /
IndustryTerm
front-end processing / transcription systems / confusion network / neural networks / context-dependent deep neural networks / recurrent neural network / possible applications / deployed meeting transcription systems / neural network / confusion networks / automatic speech recognition systems / hybrid systems / deep neural networks / meeting transcription systems / /
Movie
NNLM Adapt / /
MusicAlbum
Speech / /
Organization
MLP (MLP) / Engineering Department / AMI TTM / Toshiba Research Europe Ltd’s Cambridge Lab. / Cambridge Research Lab / University of Cambridge / US Federal Reserve / Stanford / /
Person
Catherine Breslin / Herve Bourlard / Alex Acero / Phil C. Woodland / Jan Cernock / Kate Knill / Asmaa El Hannani / Gauvain / George Dahl / Eric Wang / Adam Janin / Barbara Peskin / Sanjeev Khudanpur / Xavier Anguera Miro / Elizabeth Shriberg / Eric Brill / Steve Renals / Giulia Garau / Do Yeong Kim / Marcus Tomalin / Martial Michel / Jean Carletta / Junho Park / Michael Pitz / Tasos Anastasakos / Li Deng / Frank Diehl / Mark J F Gales / Yongqiang Wang / Gang Li / Richard Schwartz / Christophe Laprun / Elham Tabassi / Kai Yu / Dan Ellis / Hermann Ney / John Makhoul / Dong Yu / Lidia Mangu / Mark J. F. Gales / Frank Seide / Chin-Hui Lee / Holger Schwenk / Chao Zhang / Marijn Huijbregts / Petr Fousek / Lukas Burget / Daniel Povey / John S Garofolo / Tomas Mikolov / David Gelbart / Xunying Liu / John Dines / Philip C Woodland / Vincent M Stanford / Frank Wessel / Jithendra Vepa / Don Baron / Lan Wang / Frantisek Grezl / Thomas Hain / Jerome Ajot / Jonathan G Fiscus / Mike Lincoln / Nelson Morgan / P. C. Woodland / Jane Edwards / John McDonough / Martin Karafiat / Gunnar Evermann / Vincent Wan / Martin Karafi / Andreas Stolcke / Xie Chen / /
Position
target speaker for GMM-based systems / compact model / speaker / trained speaker / specific speaker / speaker / seating position / online speaker / feed-forward / non-native speaker / WER speaker / A0001 Speaker / native speaker / /
An Initial Investigation of Long-Term Adaptation for Meeting Transcription X. Chen 1 , M.J.F. Gales 1 , K. Knill 1,2 , C. Breslin 1,2 , L. Chen 2 , K. K. Chin 2 and V. Wan 2 1 Engineering Department, University of Cambri