| 2025 | ASRU | DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition. | Alexander Polok, Santosh Kesiraju, Karel Benes, Bolaji Yusuf, Luks Burget, Jan Cernock |
| 2025 | ICDAR | TextBite: A Historical Czech Document Dataset for Logical Page Segmentation. | Martin Kostelnk, Karel Benes, Michal Hradis |
| 2024 | ICASSP | Hystoc: Obtaining Word Confidences for Fusion of End-To-End ASR Systems. | Karel Benes, Martin Kocour, Luks Burget |
| 2022 | DAS | Importance of Textlines in Historical Document Classification. | Martin Kiss, Jan Koht, Karel Benes, Michal Hradis |
| 2021 | ICDAR | AT-ST: Self-training Adaptation Strategy for OCR in Domains with Limited Transcriptions. | Martin Kiss, Karel Benes, Michal Hradis |
| 2021 | Interspeech | Text Augmentation for Language Models in High Error Recognition Scenario. | Karel Benes, Luks Burget |
| 2018 | Interspeech | i-Vectors in Language Modeling: An Efficient Way of Domain Adaptation for Feed-Forward Models. | Karel Benes, Santosh Kesiraju, Luks Burget |
| 2017 | ASRU | MGB-3 but system: Low-resource ASR on Egyptian YouTube data. | Karel Vesel, Murali Karthick Baskar, Mireia Dez, Karel Benes |
| 2017 | Interspeech | Residual Memory Networks in Language Modeling: Improving the Reputation of Feed-Forward Networks. | Karel Benes, Murali Karthick Baskar, Luks Burget |