Jan Švec
Jan Švec
Department of Cybernetics, University of West Bohemia
Verified email at
Cited by
Cited by
Automatic punctuation annotation in Czech broadcast news speech
J Kolář, J Švec, J Psutka
9th Conference Speech and Computer, 2004
System for Fast Lexical and Phonetic Spoken Term Detection in a Czech Cultural Heritage Archive
J Psutka, J Švec, JV Psutka, J Vaněk, A Pražák, L Šmídl, P Ircing
EURASIP Journal on Audio, Speech, and Music Processing, 2012
Web text data mining for building large scale language modelling corpus
J Švec, J Hoidekr, D Soutner, J Vavruška
Text, Speech and Dialogue, 356-363, 2011
WISE 2014 challenge: Multi-label classification of print media articles to topics
G Tsoumakas, A Papadopoulos, W Qian, S Vologiannidis, A D’yakonov, ...
Web Information Systems Engineering–WISE 2014: 15th International Conference …, 2014
Air traffic control communication (ATCC) speech corpora and their use for ASR and TTS development
L Šmídl, J Švec, D Tihelka, J Matoušek, J Romportl, P Ircing
Language Resources and Evaluation 53, 449-464, 2019
Extension of HVS semantic parser by allowing left-right branching
F Jurčíček, J Švec, L Müller
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE …, 2008
Hierarchical discriminative model for spoken language understanding
J Švec, L Šmídl, P Ircing
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
Semi-supervised training of DNN-based acoustic model for ATC speech recognition
L Šmídl, J Švec, A Pražák, J Trmal
Speech and Computer: 20th International Conference, SPECOM 2018, Leipzig …, 2018
General framework for mining, processing and storing large amounts of electronic texts for language modeling purposes
J Švec, J Lehečka, P Ircing, L Skorkovská, A Pražák, J Vavruška, ...
Language resources and evaluation 48, 227-248, 2014
Semantic entity detection from multiple ASR hypotheses within the WFST framework
J Švec, P Ircing, L Šmídl
2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 84-89, 2013
T5g2p: Using text-to-text transfer transformer for grapheme-to-phoneme conversion
M Řezáčková, J Švec, D Tihelka
International Speech Communication Association, 2021
Comparison of czech transformers on text classification tasks
J Lehečka, J Švec
Statistical Language and Speech Processing: 9th International Conference …, 2021
Bert-based sentiment analysis using distillation
J Lehečka, J Švec, P Ircing, L Šmídl
International Conference on Statistical Language and Speech Processing, 58-70, 2020
Czech spontaneous speech corpus with structural metadata
J Kolář, J Švec, S Strassel, C Walker, D Kozlíková, J Psutka
Ninth European Conference on Speech Communication and Technology, 2005
Exploring capabilities of monolingual audio transformers using large datasets in automatic speech recognition of Czech
J Lehečka, J Švec, A Pražák, JV Psutka
arXiv preprint arXiv:2206.07627, 2022
Adjusting BERT’s pooling layer for large-scale multi-label text classification
J Lehečka, J Švec, P Ircing, L Šmídl
International Conference on Text, Speech, and Dialogue, 214-221, 2020
A Relevance Score Estimation for Spoken Term Detection Based on RNN-Generated Pronunciation Embeddings.
J Svec, JV Psutka, L Smídl, J Trmal
INTERSPEECH, 2934-2938, 2017
Prototype of Czech Spoken Dialog System with Mixed Initiative for Railway Information Service
J Švec, L Šmídl
Text, Speech and Dialogue, 568-575, 2011
On the use of grapheme models for searching in large spoken archives
J Svec, JV Psutka, J Trmal, L Smidl, P Ircing, J Sedmidubsky
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
Improving multi-label document classification of Czech news articles
J Lehečka, J Švec
International Conference on Text, Speech, and Dialogue, 307-315, 2015
The system can't perform the operation now. Try again later.
Articles 1–20