Search Results for author: Josef Psutka

Found 4 papers, 2 papers with code

Transfer Learning of Transformer-based Speech Recognition Models from Czech to Slovak

no code implementations • 7 Jun 2023 • Jan Lehečka, Josef V. Psutka, Josef Psutka

In this paper, we are comparing several methods of training the Slovak speech recognition models based on the Transformers architecture.

speech-recognition Speech Recognition +1

Paper
Add Code

Transformer-based Automatic Speech Recognition of Formal and Colloquial Czech in MALACH Project

no code implementations • 15 Jun 2022 • Jan Lehečka, Josef V. Psutka, Josef Psutka

Czech is a very specific language due to its large differences between the formal and the colloquial form of speech.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Paper
Add Code

A Comparison of Adaptation Techniques and Recurrent Neural Network Architectures

1 code implementation • 12 Jul 2018 • Jan Vanek, Josef Michalek, Jan Zelinka, Josef Psutka

Also, we published the open-source scripts to easily replicate the results and to help continue the development.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

24

Paper
Code

Recurrent DNNs and its Ensembles on the TIMIT Phone Recognition Task

1 code implementation • 19 Jun 2018 • Jan Vanek, Josef Michalek, Josef Psutka

Also, we prefer the phone recognition task because it is much more sensitive to an acoustic model quality than a large vocabulary continuous speech recognition task.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

24

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.