no code implementations • 21 May 2023 • Karel Beneš, Martin Kocour, Lukáš Burget
Furthermore, we show that utilizing Hystoc in fusion of multiple e2e ASR systems increases the gains from the fusion by up to 1\,\% WER absolute on Spanish RTVE2020 dataset.
1 code implementation • 5 Dec 2022 • Martin Kišš, Michal Hradiš, Karel Beneš, Petr Buchal, Michal Kula
This paper explores semi-supervised training for sequence tasks, such as Optical Character Recognition or Automatic Speech Recognition.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • 24 Jan 2022 • Martin Kišš, Jan Kohút, Karel Beneš, Michal Hradiš
The line-level system significantly improves results in script and font classification and in the dating task.
1 code implementation • 27 Apr 2021 • Martin Kišš, Karel Beneš, Michal Hradiš
This paper addresses text recognition for domains with limited manual annotations by a simple self-training strategy.
1 code implementation • 11 Nov 2020 • Karel Beneš, Lukáš Burget
We examine the effect of data augmentation for training of language models for speech recognition.