Suivre
Bhuvana Ramabhadran
Bhuvana Ramabhadran
Manager, Google
Adresse e-mail validée de google.com - Page d'accueil
Titre
Citée par
Citée par
Année
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
19742015
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
7452013
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
4812008
English conversational telephone speech recognition by humans and machines
G Saon, G Kurata, T Sercu, K Audhkhasi, S Thomas, D Dimitriadis, X Cui, ...
arXiv preprint arXiv:1703.02136, 2017
4632017
Deep belief networks using discriminative features for phone recognition
A Mohamed, TN Sainath, G Dahl, B Ramabhadran, GE Hinton, ...
2011 IEEE international conference on acoustics, speech and signal …, 2011
4022011
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
2982013
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
2942012
Vocabulary independent spoken term detection
J Mamou, B Ramabhadran, O Siohan
Proceedings of the 30th annual international ACM SIGIR conference on …, 2007
2522007
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
2392011
Auto-encoder bottleneck features using deep belief networks
TN Sainath, B Kingsbury, B Ramabhadran
2012 IEEE international conference on acoustics, speech and signal …, 2012
2362012
Method and apparatus for a communication device for use by a hearing impaired/mute or deaf person or in silent environments
PT Brunet, AP Ittycheriah, C Narayanaswami, MA Picheny, ...
US Patent 5,995,590, 1999
2341999
Efficient Knowledge Distillation from an Ensemble of Teachers.
T Fukuda, M Suzuki, G Kurata, S Thomas, J Cui, B Ramabhadran
Interspeech, 3697-3701, 2017
2262017
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
2002013
Deep belief nets for natural language call-routing
R Sarikaya, GE Hinton, B Ramabhadran
2011 IEEE International conference on acoustics, speech and signal …, 2011
1902011
Conversion of non-back-off language models for efficient speech decoding
E Arisoy, B Ramabhadran, A Sethy, S Chen
US Patent 9,484,023, 2016
1892016
Learning to speak fluently in a foreign language: Multilingual speech synthesis and cross-language voice cloning
Y Zhang, RJ Weiss, H Zen, Y Wu, Z Chen, RJ Skerry-Ryan, Y Jia, ...
arXiv preprint arXiv:1907.04448, 2019
1752019
Enhanced likelihood computation using regression in a speech recognition system
PV De Souza, Y Gao, M Picheny, B Ramabhadran
US Patent 6,493,667, 2002
1732002
Large-scale multilingual speech recognition with a streaming end-to-end model
A Kannan, A Datta, TN Sainath, E Weinstein, B Ramabhadran, Y Wu, ...
arXiv preprint arXiv:1909.05330, 2019
1702019
Direct acoustics-to-word models for english conversational speech recognition
K Audhkhasi, B Ramabhadran, G Saon, M Picheny, D Nahamoo
arXiv preprint arXiv:1703.07754, 2017
1662017
Kernel methods match deep neural networks on timit
PS Huang, H Avron, TN Sainath, V Sindhwani, B Ramabhadran
2014 IEEE International Conference on Acoustics, Speech and Signal …, 2014
1612014
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–20