Suivre
Brian Kingsbury
Brian Kingsbury
Distinguished Research Staff Member and Manager, IBM T. J. Watson Research Center, Yorktown Heights
Adresse e-mail validée de us.ibm.com - Page d'accueil
Titre
Citée par
Citée par
Année
Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups
G Hinton, L Deng, D Yu, GE Dahl, A Mohamed, N Jaitly, A Senior, ...
IEEE Signal processing magazine 29 (6), 82-97, 2012
140562012
Deep convolutional neural networks for large-scale speech tasks
TN Sainath, B Kingsbury, G Saon, H Soltau, A Mohamed, G Dahl, ...
Neural networks 64, 39-48, 2015
20492015
New types of deep neural network learning for speech recognition and related applications: An overview
L Deng, G Hinton, B Kingsbury
2013 IEEE international conference on acoustics, speech and signal …, 2013
16572013
Low-rank matrix factorization for deep neural network training with high-dimensional output targets
TN Sainath, B Kingsbury, V Sindhwani, E Arisoy, B Ramabhadran
2013 IEEE international conference on acoustics, speech and signal …, 2013
8162013
Data augmentation for deep neural network acoustic modeling
X Cui, V Goel, B Kingsbury
IEEE/ACM Transactions on Audio, Speech, and Language Processing 23 (9), 1469 …, 2015
5562015
Boosted MMI for model and feature-space discriminative training
D Povey, D Kanevsky, B Kingsbury, B Ramabhadran, G Saon, ...
2008 IEEE International Conference on Acoustics, Speech and Signal …, 2008
4992008
fMPE: Discriminatively trained features for speech recognition
D Povey, B Kingsbury, L Mangu, G Saon, H Soltau, G Zweig
Proceedings.(ICASSP'05). IEEE International Conference on Acoustics, Speech …, 2005
3712005
Robust speech recognition using the modulation spectrogram
BED Kingsbury, N Morgan, S Greenberg
Speech communication 25 (1-3), 117-132, 1998
3651998
Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling
B Kingsbury
2009 IEEE International Conference on Acoustics, Speech and Signal …, 2009
3542009
Improvements to deep convolutional neural networks for LVCSR
TN Sainath, B Kingsbury, A Mohamed, GE Dahl, G Saon, H Soltau, ...
2013 IEEE workshop on automatic speech recognition and understanding, 315-320, 2013
3182013
Deep neural network language models
E Arisoy, TN Sainath, B Kingsbury, B Ramabhadran
Proceedings of the NAACL-HLT 2012 Workshop: Will We Ever Really Replace the …, 2012
3162012
The modulation spectrogram: In pursuit of an invariant representation of speech
S Greenberg, BED Kingsbury
1997 IEEE international conference on acoustics, speech, and signal …, 1997
2991997
Scalable Minimum Bayes Risk Training of Deep Neural Network Acoustic Models Using Distributed Hessian-free Optimization.
B Kingsbury, TN Sainath, H Soltau
Interspeech, 10-13, 2012
2842012
Very deep multilingual convolutional neural networks for LVCSR
T Sercu, C Puhrsch, B Kingsbury, Y LeCun
2016 IEEE international conference on acoustics, speech and signal …, 2016
2812016
Making deep belief networks effective for large vocabulary continuous speech recognition
TN Sainath, B Kingsbury, B Ramabhadran, P Fousek, P Novak, ...
2011 IEEE Workshop on Automatic Speech Recognition & Understanding, 30-35, 2011
2502011
Auto-encoder bottleneck features using deep belief networks
TN Sainath, B Kingsbury, B Ramabhadran
2012 IEEE international conference on acoustics, speech and signal …, 2012
2462012
Audio-visual deep learning for noise robust speech recognition
J Huang, B Kingsbury
2013 IEEE international conference on acoustics, speech and signal …, 2013
2322013
Method and system for efficient spoken term detection using confusion networks
BED Kingsbury, HK Kuo, L Mangu, H Soltau
US Patent 9,196,243, 2015
2262015
Classifier-based system combination for spoken term detection
BED Kingsbury, HKJ Kuo, LL Mangu, H Soltau
US Patent 9,477,753, 2016
2182016
Learning filter banks within a deep neural network framework
TN Sainath, B Kingsbury, A Mohamed, B Ramabhadran
2013 IEEE workshop on automatic speech recognition and understanding, 297-302, 2013
2092013
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–20