引用次数
引用: 565
H-指数: 13
I10-指数 : 19
出版物: 59
Speaker normalization with the band-pass transform
P.L. Dognin , A. El-Jaroudi
asilomar conference on signals, systems and computers 2 1894 -1899
2003
Generative Feature Matching Networks
Pierre Dognin , Cicero Nogueira dos Santos , Youssef Mroueh , Inkit Padhi
2
2018
Learning Implicit Generative Models by Matching Perceptual Features
Pierre Dognin , Cicero Nogueira dos Santos , Youssef Mroueh , Inkit Padhi
arXiv: Computer Vision and Pattern Recognition
14
2019
Learning Implicit Text Generation via Feature Matching
Pierre Dognin , Cicero Nogueira dos Santos , Payel Das , Vijil Chenthamarakshan
arXiv: Computation and Language
2020
Evaluating Deep Scattering Spectra with deep neural networks on large scale spontaneous speech task
Petr Fousek , Pierre Dognin , Vaibhava Goel
international conference on acoustics, speech, and signal processing 4550 -4554
3
2015
Robust speech recognition using dynamic noise adaptation
Steven Rennie , Pierre Dognin , Petr Fousek
2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 4592 -4595
6
2011
Direct product based deep belief networks for automatic speech recognition
Petr Fousek , Steven Rennie , Pierre Dognin , Vaibhava Goel
international conference on acoustics, speech, and signal processing 3148 -3152
2
2013
The 2001 BYBLOS English large vocabulary conversational speech recognition system
Spyros Matsoukas , Thomas Colthurst , Owen Kimball , Alex Solomonoff
international conference on acoustics, speech, and signal processing 1 721 -724
5
2002
Combining stochastic average gradient and Hessian-free optimization for sequence training of deep neural networks
Pierre Dognin , Vaibhava Goel
ieee automatic speech recognition and understanding workshop 321 -325
7
2013
Fair infinitesimal jackknife: Mitigating the influence of biased training data points without refitting
Prasanna Sattigeri , Soumya Ghosh , Inkit Padhi , Pierre Dognin
Advances in Neural Information Processing Systems 35 35894 -35906
2022
Systems and methods for combining stochastic average gradient and hessian-free optimization for sequence training of deep neural networks
Pierre Dognin , Vaibhava Goel
22
2016
Systems and methods for combining stochastic average gradient and hessian-free optimization for sequence training of deep neural networks
Pierre Dognin , Vaibhava Goel
5
2017
Model restructuring for client and server based automatic speech recognition
Pierre Dognin , Vaibhava Goel , John R Hershey , Peder A Olsen
5
2014
System and method for dynamic noise adaptation for robust automatic speech recognition
Steven J Rennie , Pierre Dognin , Petr Fousek
10
2015
Detectors for safe and reliable llms: Implementations, uses, and limitations
Swapnaja Achintalwar , Adriana Alvarado Garcia , Ateret Anaby-Tavor , Ioana Baldini
arXiv preprint arXiv:2403.06009
2
2024
Wasserstein Barycenter Model Ensembling
Pierre Dognin , Igor Melnyk , Youssef Mroueh , Jerret Ross
ICLR 2019
30
2019
Image Captioning as an Assistive Technology: Lessons Learned from VizWiz 2020 Challenge
Pierre Dognin , Igor Melnyk , Youssef Mroueh , Inkit Padhi
Journal of Artificial Intelligence Research 73 437 -459
42
2022
Auditing and Generating Synthetic Data with Controllable Trust Trade-offs
Brian Belgodere , Pierre Dognin , Adam Ivankay , Igor Melnyk
arXiv preprint arXiv:2304.10819
6
2023
The incentive gap in data work in the era of large models
Katy Ilonka Gero , Payel Das , Pierre Dognin , Inkit Padhi
Nature Machine Intelligence 5 ( 6) 565 -567
2
2023
Alleviating Noisy Data in Image Captioning with Cooperative Distillation
Pierre Dognin , Igor Melnyk , Youssef Mroueh , Inkit Padhi
arXiv preprint arXiv:2012.11691
2
2020
Youssef Mroueh Inkit Padhi Vaibhava Goel Tom Sercu Steven J. Rennie Mattia Rigotti Cicero Nogueira dos Santos John Hershey Peder A Olsen Xiaodong Cui Brian Michael Belgodere Erik Altman Ravi Nair Bowen Zhou jayadev billa Fred Richardson Spyros Matsoukas Thomas Colthurst Giuseppe Romano Chinmay Hegde