Follow
Pierre Dognin
Pierre Dognin
IBM Research AI
Verified email at us.ibm.com - Homepage
Title
Cited by
Cited by
Year
Adversarial semantic alignment for improved image captions
P Dognin, I Melnyk, Y Mroueh, J Ross, T Sercu
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2019
30*2019
Wasserstein barycenter model ensembling
P Dognin, I Melnyk, Y Mroueh, J Ross, CD Santos, T Sercu
arXiv preprint arXiv:1902.04999, 2019
202019
Systems and methods for combining stochastic average gradient and hessian-free optimization for sequence training of deep neural networks
P Dognin, V Goel
US Patent 9,483,728, 2016
182016
Tabular transformers for modeling multivariate time series
I Padhi, Y Schiff, I Melnyk, M Rigotti, Y Mroueh, P Dognin, J Ross, R Nair, ...
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
162021
Acoustic modeling with bootstrap and restructuring for low-resourced languages
X Cui, J Xue, PL Dognin, UV Chaudhari, B Zhou
Eleventh Annual Conference of the International Speech Communication Association, 2010
162010
Combining stochastic average gradient and hessian-free optimization for sequence training of deep neural networks
P Dognin, V Goel
2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 321-325, 2013
142013
Hidden markov acoustic modeling with bootstrap and restructuring for low-resourced languages
X Cui, J Xue, X Chen, PA Olsen, PL Dognin, UV Chaudhari, JR Hershey, ...
IEEE Transactions on Audio, Speech, and Language Processing 20 (8), 2252-2264, 2012
142012
Learning implicit generative models by matching perceptual features
CN Santos, Y Mroueh, I Padhi, P Dognin
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2019
122019
Improved image captioning with adversarial semantic alignment
I Melnyk, T Sercu, PL Dognin, J Ross, Y Mroueh
arXiv preprint arXiv:1805.00063, 2018
122018
Factorial hidden restricted boltzmann machines for noise robust speech recognition
SJ Rennie, P Fousek, PL Dognin
2012 IEEE International Conference on Acoustics, Speech and Signal …, 2012
112012
The 2001 Byblos English large vocabulary conversational speech recognition system
S Matsoukas, T Colthurst, O Kimball, A Solomonoff, F Richardson, ...
2002 IEEE International Conference on Acoustics, Speech, and Signal …, 2002
112002
Parameter optimization for vocal tract length normalization
P Dognin, A El-Jaroudi, J Billa
2000 IEEE International Conference on Acoustics, Speech, and Signal …, 2000
112000
Refactoring acoustic models using variational density approximation
PL Dognin, JR Hershey, V Goel, PA Olsen
2009 IEEE International Conference on Acoustics, Speech and Signal …, 2009
102009
Refactoring acoustic models using variational Expectation-Maximization
PL Dognin, JR Hershey, V Goel, PA Olsen
Tenth Annual Conference of the International Speech Communication Association, 2009
92009
Image captioning as an assistive technology: Lessons learned from vizwiz 2020 challenge
P Dognin, I Melnyk, Y Mroueh, I Padhi, M Rigotti, J Ross, Y Schiff, ...
arXiv preprint arXiv:2012.11696, 2020
82020
Evaluating deep scattering spectra with deep neural networks on large scale spontaneous speech task
P Fousek, P Dognin, V Goel
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
82015
System and method for dynamic noise adaptation for robust automatic speech recognition
SJ Rennie, P Dognin, P Fousek
US Patent 8,972,256, 2015
82015
Robust speech recognition using dynamic noise adaptation
S Rennie, P Dognin, P Fousek
2011 IEEE International Conference on Acoustics, Speech and Signal …, 2011
82011
Annealed dropout trained maxout networks for improved lvcsr
SJ Rennie, PL Dognin, X Cui, V Goel
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
62015
A fast, accurate approximation to log likelihood of Gaussian mixture models
PL Dognin, V Goel, JR Hershey, PA Olsen
2009 IEEE International Conference on Acoustics, Speech and Signal …, 2009
62009
The system can't perform the operation now. Try again later.
Articles 1–20