Prati
Samuel Thomas
Samuel Thomas
IBM Research AI
Potvrđena adresa e-pošte na us.ibm.com - Početna stranica
Naslov
Citirano
Citirano
Godina
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
4472017
The subspace Gaussian mixture model—A structured model for speech recognition
D Povey, L Burget, M Agarwal, P Akyazi, F Kai, A Ghoshal, O Glembek, ...
Computer Speech & Language 25 (2), 404-439, 2011
3812011
Subspace Gaussian mixture models for speech recognition
D Povey, L Burget, M Agarwal, P Akyazi, K Feng, A Ghoshal, NK Goel, ...
2010 IEEE International Conference on Acoustics, Speech and Signal …, 2010
2402010
Multilingual acoustic modeling for speech recognition based on subspace Gaussian mixture models
L Burget, P Schwarz, M Agarwal, P Akyazi, K Feng, A Ghoshal, N Goel, ...
2010 IEEE International Conference on Acoustics, Speech and Signal …, 2010
2052010
Efficient Knowledge Distillation from an Ensemble of Teachers.
T Fukuda, M Suzuki, G Kurata, S Thomas, J Cui, B Ramabhadran
Interspeech, 3697-3701, 2017
2042017
Deep neural network features and semi-supervised training for low resource speech recognition
S Thomas, ML Seltzer, K Church, H Hermansky
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
1722013
Analyzing convolutional neural networks for speech activity detection in mismatched acoustic conditions
S Thomas, S Ganapathy, G Saon, H Soltau
ICASSP, 2014
1332014
Multilingual MLP features for low-resource LVCSR systems
S Thomas, S Ganapathy, H Hermansky
1312012
Avlnet: Learning audio-visual language representations from instructional videos
A Rouditchenko, A Boggust, D Harwath, B Chen, D Joshi, S Thomas, ...
arXiv preprint arXiv:2006.09199, 2020
1292020
A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition.
A Jansen, E Dupoux, S Goldwater, M Johnson, S Khudanpur, K Church, ...
ICASSP, 8111-8115, 2013
1152013
Recognition of reverberant speech using frequency domain linear prediction
S Thomas, S Ganapathy, H Hermansky
IEEE Signal Processing Letters 15, 681-684, 2008
1122008
Rapid evaluation of speech representations for spoken term discovery
MA Carlin, S Thomas, A Jansen, H Hermansky
Twelfth Annual Conference of the International Speech Communication Association, 2011
1052011
Everything at Once-Multi-Modal Fusion Transformer for Video Retrieval
N Shvetsova, B Chen, A Rouditchenko, S Thomas, B Kingsbury, RS Feris, ...
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
962022
Cross-lingual and multi-stream posterior features for low resource LVCSR systems
S Thomas, S Ganapathy, H Hermansky
Eleventh Annual Conference of the International Speech Communication Association, 2010
872010
Invariant Representations for Noisy Speech Recognition
D Serdyuk, K Audhkhasi, P Brakel, B Ramabhadran, S Thomas, Y Bengio
arXiv preprint arXiv:1612.01928, 2016
792016
Annealed dropout training of deep networks
SJ Rennie, V Goel, S Thomas
2014 IEEE Spoken Language Technology Workshop (SLT), 159-164, 2014
792014
Joint modeling of accents and acoustics for multi-accent speech recognition
X Yang, K Audhkhasi, A Rosenberg, S Thomas, B Ramabhadran, ...
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
762018
Weak top-down constraints for unsupervised acoustic model training
A Jansen, S Thomas, H Hermansky
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
682013
Robust language identification using convolutional neural network features
S Ganapathy, K Han, S Thomas, M Omar, MV Segbroeck, SS Narayanan
Fifteenth Annual Conference of the International Speech Communication …, 2014
672014
The IBM Speech Activity Detection System for the DARPA RATS Program
G Saon, S Thomas, H Soltau, S Ganapathy, B Kingsbury
672013
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20