Katedra kybernetiky / Department of Cybernetics

Zobrazit statistiky

Kolekce


Poslední příspěvky

Káš, Martin , Polreich, Václav
Development of a Robust Wireless Mesh Network Modules for Proximity Sensing During Assembly Process of a Steam Turbine

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&...

Neduchal, Petr , Železný, Miloš
Environment Classification Approach for Mobile Robots

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 ...

Matoušek, Jindřich , Vraštil, Michal
Context-Aware XGBoost for Glottal Closure Instant Detection in Speech Signal

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. ...

Švec, Jan , Lehečka, Jan , Šmídl, Luboš , Ircing, Pavel
Automatic Correction of i/y Spelling in Czech ASR Output

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&#...

Hanzlíček, Zdeněk , Vít, Jakub
LSTM-Based Speech Segmentation Trained on Different Foreign Languages

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&...