AT-ST: self-training adaptation strategy for OCR in domains with limited transcriptions M Kišš, K Beneš, M Hradiš International Conference on Document Analysis and Recognition, 463-477, 2021 | 15 | 2021 |
i-Vectors in language modeling: An efficient way of domain adaptation for feed-forward models K Beneš, S Kesiraju, L Burget Proc. Interspeech 2018, 3383-3387, 2018 | 7 | 2018 |
Residual Memory Networks in Language Modeling: Improving the Reputation of Feed-Forward Networks K Beneš, MK Baskar, L Burget Proc. Interspeech 2017, 284-288, 2017 | 7 | 2017 |
MGB-3 BUT system: Low-resource ASR on Egyptian YouTube data K Veselý, BK Murali, M Diez, K Beneš 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2017 | 5 | 2017 |
Importance of textlines in historical document classification M Kišš, J Kohút, K Beneš, M Hradiš International Workshop on Document Analysis Systems, 158-170, 2022 | 4 | 2022 |
Text Augmentation for Language Models in High Error Recognition Scenario K Beneš, L Burget arXiv preprint arXiv:2011.06056, 2020 | 3 | 2020 |
BUT system for CHiME-6 challenge K Zmolıková, M Kocour, NF Landini, K Beneš, M Karafiát, KH Vydana, ... Proceedings of CHiME 2020 Virtual Workshop. University of Sheffield, 1-3, 2020 | 2 | 2020 |
Hystoc: Obtaining word confidences for fusion of end-to-end ASR systems K Beneš, M Kocour, L Burget ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and …, 2024 | 1 | 2024 |
Randomly Sparsed Recurrent Neural Networks for Language Modeling K Beneš Excel@ FIT, Student Conference, 2016 | 1 | 2016 |
Finite State Grammars as Language Models for Automatic Speech Recognition K Beneš Bachelor’s thesis, Faculty of Information Technology, Brno University of …, 2014 | 1 | 2014 |
BUT CHiME-7 system description M Karafiát, K Veselý, I Szöke, L Mošner, K Beneš, M Witkowski, G Barchi, ... arXiv preprint arXiv:2310.11921, 2023 | | 2023 |
SoftCTC—semi-supervised learning for text recognition using soft pseudo-labels M Kišš, M Hradiš, K Beneš, P Buchal, M Kula International Journal on Document Analysis and Recognition (IJDAR), 1-17, 2023 | | 2023 |
BUT Systems for IWSLT 2023 Marathi-Hindi Low Resource Speech Translation Task S Kesiraju, K Beneš, M Tikhonov, J Černocký Proceedings of the 20th International Conference on Spoken Language …, 2023 | | 2023 |
SoftCTC $\unicode {x2013} $ Semi-Supervised Learning for Text Recognition using Soft Pseudo-Labels M Kišš, M Hradiš, K Beneš, P Buchal, M Kula arXiv preprint arXiv:2212.02135, 2022 | | 2022 |
BUT System for CHiME-6 Challenge K Zmolikova, M Kocour, F Landini, K Beneš, M Karafiát, HK Vydana, ... | | |
Unsupervised Language Model Adaptation for Speech Recognition with no Extra Resources K Beneš, K Irie, E Beck, R Schlüter, H Ney | | |
Speech recognition system in the A-PiMod project K Beneš | | |