Članki z zahtevami za javni dostop - Samuel ThomasVeč o tem
Na voljo nekje: 13
Recognition of reverberant speech using frequency domain linear prediction
S Thomas, S Ganapathy, H Hermansky
IEEE Signal Processing Letters 15, 681-684, 2008
Zahteve: Swiss National Science Foundation
Multimodal clustering networks for self-supervised learning from unlabeled videos
B Chen, A Rouditchenko, K Duarte, H Kuehne, S Thomas, A Boggust, ...
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
Zahteve: US Office of the Director of National Intelligence
Phoneme recognition using spectral envelope and modulation frequency features
S Thomas, S Ganapathy, H Hermansky
2009 IEEE International Conference on Acoustics, Speech and Signal …, 2009
Zahteve: Swiss National Science Foundation
Modulation frequency features for phoneme recognition in noisy speech
S Ganapathy, S Thomas, H Hermansky
The Journal of the Acoustical Society of America 125 (1), EL8-EL12, 2009
Zahteve: Swiss National Science Foundation
Training Spoken Language Understanding Systems with Non-Parallel Speech and Text
L Sarı, S Thomas, M Hasegawa-Johnson
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
Zahteve: US National Science Foundation
Auxiliary Networks for Joint Speaker Adaptation and Speaker Change Detection
L Sari, M Hasegawa-Johnson, S Thomas
IEEE/ACM Transactions on Audio, Speech, and Language Processing 29, 324-333, 2020
Zahteve: US National Science Foundation
Applications of signal analysis using autoregressive models for amplitude modulation
S Ganapathy, S Thomas, P Motlicek, H Hermansky
2009 IEEE Workshop on Applications of Signal Processing to Audio and …, 2009
Zahteve: Swiss National Science Foundation
Spectro-Temporal Features for Automatic Speech Recognition using Linear Prediction in Spectral Domain
S Thomas, S Ganapathy, H Hermansky
Proceedings of the 16th European Signal Processing Conference (EUSIPCO 2008 …, 2008
Zahteve: Swiss National Science Foundation
Tandem representations of spectral envelope and modulation frequency features for ASR.
S Thomas, S Ganapathy, H Hermansky
INTERSPEECH, 2955-2958, 2009
Zahteve: Swiss National Science Foundation
What When and Where? Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions
B Chen, N Shvetsova, A Rouditchenko, D Kondermann, S Thomas, ...
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024
Zahteve: US Department of Defense, Federal Ministry of Education and Research, Germany
Speech recognition with segmental conditional random fields: Final report from the 2010 JHU summer workshop
G Zweig, P Nguyen, D Van Compernolle, K Demuynck, H Hermansky, ...
Technical report, 2010
Zahteve: Research Foundation (Flanders)
Hilbert envelope based features for far-field speech recognition
S Thomas, S Ganapathy, H Hermansky
International Workshop on Machine Learning for Multimodal Interaction, 119-124, 2008
Zahteve: Swiss National Science Foundation
Convkt: Conversation-level knowledge transfer for context aware end-to-end spoken language understanding
V Sunder, E Fosler-Lussier, S Thomas, HKJ Kuo, B Kingsbury
ISCA, 2023
Zahteve: US National Science Foundation
Podatke o objavi in financiranju samodejno določi računalniški program