In this paper, we present our progress in pre-training monolingual Transformers for Czech and contribute to the research community by releasing our models for public. The need for such models emerged from our effort to employ Transformers in our language-specific tasks, but we foun...

This work presents a pipeline for processing digitally scanned documents, reading their textual content, and storing it in a dataset for the purpose of information retrieval. The pipeline is able to handle images of various quality, whether they were obtained by a digital scanner&#...

The black-box behavior of Convolutional Neural Networks is one of the biggest obstacles to the development of a standardized validation process. Methods for analyzing and validating neural networks currently rely on approaches and metrics provided by the scientific community without considering&#...

This paper is devoted to the Bayesian state estimation of the nonlinear stochastic dynamic systems. The stress is laid on Gaussian unscented Kalman filter (UKF) and, in particular, on a setting of its scaling parameter, which significantly affects the UKF estimation performance. Compare...

Mean square error matrices belong to key concepts in decentralised estimation. They assess the quality of estimates and are essential for the optimisation of the estimation fusion. In the case of a missing knowledge, sets of admissible matrices are replaced by their bounds and ...

The paper deals with active fault diagnosis of stochastic large-scale systems consisting of several subsystems with separate inputs and observations, which are coupled through the system state. The subsystems are described by multiple models expressing their fault-free and faulty behaviour. The&#...

Confidence sets are random sets constructed in such a way that the probability that they contain the estimated parameter achieves a chosen level. This paper deals with combining information from two estimates and discusses several designs with respect to various degrees of knowledge...

The paper deals with active fault diagnosis of stochastic large scale systems for the cases when the fault in one subsystem may change probability of occurrence of faults in other subsystems. The multiple model framework is considered and each subsystem is represented by a set...

The paper deals with the estimation of noise parameters of a linear time-varying system. In particular, the stress is laid on the state-space models, where the state and measurement noises are described by the Gaussian sum probability density functions. The recently introduced measureme...

Available feedback architectures with time delay based signal shapers are outlined and studied with the objective to determine the channels in which the flexible mode compensation (by the shaper) takes place. As the main result, a systematic methodology for the robust controller design&...

We introduce a unified Grapheme-to-phoneme conversion framework based on the composition of deep neural networks. In contrary to the usual approaches building the G2P frameworks from the dictionary, we use whole phrases, which allows us to capture various language properties, e.g. cross-word...

The goal of the paper is to share experience with the use of hardware-in-the-loop (HIL) simulators in a control-engineering course being taught at the University of West Bohemia. The hardware simulators were introduced recently in the course curriculum aiming to get more realistic ...

This paper deals with a design of wireless proximity sensing between the stator and rotor of a steam turbine during a final steps of an assembly. The result of this assembly process is an optimal setting of the seal which affects overall turbine efficiency. An innovative&...

The type of environment plays an essential role in mobile robotics. Autonomous robots usually work in static and single type environments. Unfortunately, in the real world, there are many situations when the type of the environment changes. This paper deals with the design of ...

In this paper, we continue to investigate the use of classifiers for the automatic detection of glottal closure instants (GCIs) in the speech signal. We introduce context to extreme gradient boosting (XGBoost) and show that the context-aware XGBoost outperforms its context-free version. ...

This paper concentrates on the design and evaluation of the method that would be able to automatically correct the spelling of i/y in the Czech words at the output of the ASR decoder. After analysis of both the Czech grammar rules and the data, we have decided&#...

This paper describes experiments on speech segmentation by using bidirectional LSTM neural networks. The networks were trained on various languages (English, German, Russian and Czech), segmentation experiments were performed on 4 Czech professional voices. To be able to use various combinations&...

Turbine-generator torsional vibration is linked to electrical events in the power grid by the generator air-gap torque. Modern power systems are subject to gradual transformation by increasing flexibility demands and incorporation of renewable resources. As a result, electrical transient events a...

Building accurate knowledge of the identity, the geographic distribution and the evolution of species is essential for the sustainable development of humanity, as well as for biodiversity conservation. However, the difficulty of identifying plants and animals in the field is hindering the&#x...

Annotating a dataset for training a Supervised Machine Learning algorithm is time and annotator’s attention intensive. Our goal was to create a tool that would enable us to create annotations of the dataset with minimal demands on expert’s time. Inspired by applications such as...