Karel Benes

According to our database, Karel Benes authored at least 17 papers between 1979 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of three.

2025

Jazykové modely pro nedokonalé systémy rozpoznání řeči a písma ; Language models supporting imperfect handwriting and speech recognition systems.

Karel Benes

PhD thesis, 2025

BenCzechMark : A Czech-Centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism.

Martin Fajcik, Martin Docekal, Jan Dolezal, Karel Ondrej, Karel Benes, Jan Kapsa, Pavel Smrz, Alexander Polok, Michal Hradis, Zuzana Neverilová, Ales Horák, Radoslav Sabol, Michal Stefánik, Adam Jirkovsky, David Adamczyk, Petr Hyner, Jan Hula, Hynek Kydlícek

Trans. Assoc. Comput. Linguistics, 2025

TextBite: A Historical Czech Document Dataset for Logical Page Segmentation.

Martin Kostelník, Karel Benes, Michal Hradis

Proceedings of the Document Analysis and Recognition - ICDAR 2025 Workshops, 2025

DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition.

Alexander Polok, Santosh Kesiraju, Karel Benes, Bolaji Yusuf, Lukás Burget, Jan Cernocký

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2025

2024

SoftCTC - semi-supervised learning for text recognition using soft pseudo-labels.

Martin Kiss, Michal Hradis, Karel Benes, Petr Buchal, Michal Kula

Int. J. Document Anal. Recognit., June, 2024

Hystoc: Obtaining Word Confidences for Fusion of End-To-End ASR Systems.

Karel Benes, Martin Kocour, Lukás Burget

Proceedings of the IEEE International Conference on Acoustics, 2024

2023

BUT CHiME-7 system description.

Martin Karafiát, Karel Veselý, Igor Szöke, Ladislav Mosner, Karel Benes, Marcin Witkowski, Germán Barchi, Leonardo Pepino

CoRR, 2023

BUT Systems for IWSLT 2023 Marathi - Hindi Low Resource Speech Translation Task.

Santosh Kesiraju, Karel Benes, Maksim Tikhonov, Jan Cernocký

Proceedings of the 20th International Conference on Spoken Language Translation, 2023

2022

SoftCTC $\unicode{x2013}$ Semi-Supervised Learning for Text Recognition using Soft Pseudo-Labels.

Martin Kiss, Michal Hradis, Karel Benes, Petr Buchal, Michal Kula

CoRR, 2022

BCN2BRNO: ASR System Fusion for Albayzin 2022 Speech to Text Challenge.

Martin Kocour, Jahnavi Umesh, Martin Karafiát, Jan Svec, Fernando López, Jordi Luque, Karel Benes, Mireia Díez, Igor Szöke, Karel Veselý, Lukás Burget, Jan Cernocký

Proceedings of the 6th International Conference, 2022

Importance of Textlines in Historical Document Classification.

Martin Kiss, Jan Kohút, Karel Benes, Michal Hradis

Proceedings of the Document Analysis Systems - 15th IAPR International Workshop, 2022

2021

Text Augmentation for Language Models in High Error Recognition Scenario.

Karel Benes, Lukás Burget

Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

AT-ST: Self-training Adaptation Strategy for OCR in Domains with Limited Transcriptions.

Martin Kiss, Karel Benes, Michal Hradis

Proceedings of the 16th International Conference on Document Analysis and Recognition, 2021

2018

i-Vectors in Language Modeling: An Efficient Way of Domain Adaptation for Feed-Forward Models.

Karel Benes, Santosh Kesiraju, Lukás Burget

Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018

2017

Residual Memory Networks in Language Modeling: Improving the Reputation of Feed-Forward Networks.

Karel Benes, Murali Karthick Baskar, Lukás Burget

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

MGB-3 but system: Low-resource ASR on Egyptian YouTube data.

Karel Veselý, Murali Karthick Baskar, Mireia Díez, Karel Benes

Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop, 2017

1979

On accuracy and development of outputs in roots modelling.

Karel Benes

Kybernetika, 1979