Result Number | Material Type | Add to My Shelf Action | Record Details and Options |
---|---|---|---|
1 |
Material Type: magazinearticle
|
![]() |
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsHinton, G. ; Li Deng ; Dong Yu ; Dahl, G. E. ; Mohamed, A. ; Jaitly, N. ; Senior, Andrew ; Vanhoucke, V. ; Nguyen, P. ; Sainath, T. N. ; Kingsbury, B.IEEE signal processing magazine, 2012-11, Vol.29 (6), p.82-97New York: IEEETexto completo disponível |
2 |
Material Type: Ata de Congresso
|
![]() |
Auto-encoder bottleneck features using deep belief networksSainath, T. N. ; Kingsbury, B. ; Ramabhadran, B.2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012, p.4153-4156IEEETexto completo disponível |
3 |
Material Type: Ata de Congresso
|
![]() |
Making Deep Belief Networks effective for large vocabulary continuous speech recognitionSainath, T. N. ; Kingsbury, B. ; Ramabhadran, B. ; Fousek, P. ; Novak, P. ; Mohamed, A.-R2011 IEEE Workshop on Automatic Speech Recognition & Understanding, 2011, p.30-35IEEETexto completo disponível |
4 |
Material Type: Ata de Congresso
|
![]() |
The IBM 2011 GALE Arabic speech transcription systemMangu, L. ; Hong-Kwang Kuo ; Chu, S. ; Kingsbury, B. ; Saon, G. ; Soltau, H. ; Biadsy, F.2011 IEEE Workshop on Automatic Speech Recognition & Understanding, 2011, p.272-277IEEETexto completo disponível |
5 |
Material Type: Ata de Congresso
|
![]() |
Lattice-based optimization of sequence classification criteria for neural-network acoustic modelingKingsbury, B.2009 IEEE International Conference on Acoustics, Speech and Signal Processing, 2009, p.3761-3764IEEETexto completo disponível |
6 |
Material Type: Ata de Congresso
|
![]() |
Boosted MMI for model and feature-space discriminative trainingPovey, D. ; Kanevsky, D. ; Kingsbury, B. ; Ramabhadran, B. ; Saon, G. ; Visweswariah, K.2008 IEEE International Conference on Acoustics, Speech and Signal Processing, 2008, p.4057-4060IEEETexto completo disponível |
7 |
Material Type: Ata de Congresso
|
![]() |
Discriminative Training of Decoding Graphs for Large Vocabulary Continuous Speech RecognitionKuo, H. -K. J. ; Kingsbury, B. ; Zweig, G.2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07, 2007, Vol.4, p.IV-45-IV-48IEEETexto completo disponível |
8 |
Material Type: Ata de Congresso
|
![]() |
fMPE: discriminatively trained features for speech recognitionPovey, D. ; Kingsbury, B. ; Mangu, L. ; Saon, G. ; Soltau, H. ; Zweig, G.Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005, 2005, Vol.1, p.I/961-I/964 Vol. 1IEEETexto completo disponível |
9 |
Material Type: Ata de Congresso
|
![]() |
Constructing ensembles of ASR systems using randomized decision treesSiohan, O. ; Ramabhadran, B. ; Kingsbury, B.Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005, 2005, Vol.1, p.I/197-I/200 Vol. 1IEEETexto completo disponível |
10 |
Material Type: Ata de Congresso
|
![]() |
An evaluation of a nonlinear feature transformation for conversational speech recognitionOmar, M.K. ; Kingsbury, B.2004 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2004, Vol.1, p.I-785IEEETexto completo disponível |