Josef Michalek

According to our database, Josef Michalek authored at least 7 papers between 2017 and 2023.

Collaborative distances:

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

2023

Ensemble of Deep Neural Network Models for MOS Prediction.

Marie Kunesová, Jindrich Matousek, Jan Lehecka, Jan Svec, Josef Michálek, Daniel Tihelka, Martin Bulín, Zdenek Hanzlícek, Markéta Rezácková

Proceedings of the IEEE International Conference on Acoustics, 2023

2019

Tuning of Acoustic Modeling and Adaptation Technique for a Real Speech Recognition Task.

Jan Vanek, Josef Michálek, Josef Psutka

Proceedings of the Statistical Language and Speech Processing, 2019

2018

A Survey of Recent DNN Architectures on the TIMIT Phone Recognition Task.

Josef Michálek, Jan Vanek

Proceedings of the Text, Speech, and Dialogue - 21st International Conference, 2018

Recurrent DNNs and Its Ensembles on the TIMIT Phone Recognition Task.

Jan Vanek, Josef Michálek, Josef Psutka

Proceedings of the Speech and Computer - 20th International Conference, 2018

A Comparison of Adaptation Techniques and Recurrent Neural Network Architectures.

Jan Vanek, Josef Michálek, Jan Zelinka, Josef Psutka

Proceedings of the Statistical Language and Speech Processing, 2018

2017

A GPU-Architecture Optimized Hierarchical Decomposition Algorithm for Support Vector Machine Training.

Jan Vanek, Josef Michalek, Josef Psutka

IEEE Trans. Parallel Distributed Syst., 2017

A Comparison of Support Vector Machines Training GPU-Accelerated Open Source Implementations.

Jan Vanek, Josef Michalek, Josef Psutka

CoRR, 2017