logo Idiap Research Institute        
Project SHISSM
Name: SHISSM

Publications of project SHISSM
2022
Autoencoders Reloaded, Hervé Bourlard and Selen Hande Kabil, in: Springer Biological Cybernetics, 2022
[DOI]
[URL]
Efficient Transformer-Based Speech Recognition, Apoorv Vyas, École polytechnique fédérale de Lausanne, 2022
attachment
[DOI]
2021
LATTICE-FREE MMI ADAPTATION OF SELF-SUPERVISED PRETRAINED ACOUSTIC MODELS, Apoorv Vyas, Srikanth Madikeri and Hervé Bourlard, in: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 2021
[URL]
2020
Fast Transformers with Clustered Attention, Apoorv Vyas, Angelos Katharopoulos and Francois Fleuret, in: Proceedings of the International Conference on Neural Information Processing Systems, 2020
2019
ANALYZING UNCERTAINTIES IN SPEECH RECOGNITION USING DROPOUT, Apoorv Vyas, Pranay Dighe, Sibo Tong and Hervé Bourlard, in: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019