Follow
Jakub Vít
Jakub Vít
Katedra kybernetiky, Fakulta aplikovaných věd
Verified email at ntis.zcu.cz
Title
Cited by
Cited by
Year
CHiVE: Varying prosody in speech synthesis with a linguistically driven dynamic hierarchical conditional variational network
T Kenter, V Wan, CA Chan, R Clark, J Vit
International Conference on Machine Learning, 3331-3340, 2019
692019
Google's Next-Generation Real-Time Unit-Selection Synthesizer Using Sequence-to-Sequence LSTM-Based Autoencoders.
V Wan, Y Agiomyrgiannakis, H Silen, J Vit
INTERSPEECH, 1143-1147, 2017
492017
Current state of text-to-speech system ARTIC: a decade of research on the field of speech technologies
D Tihelka, Z Hanzlíček, M Jůzová, J Vít, J Matoušek, M Grůber
International Conference on Text, Speech, and Dialogue, 369-378, 2018
332018
Improving automatic dubbing with subtitle timing optimisation using video cut detection
J Matoušek, J Vít
2012 IEEE International Conference on Acoustics, Speech and Signal …, 2012
162012
Text-to-speech synthesis using an autoencoder
BH Chun, J Gonzalvo, C Chan, I Agiomyrgiannakis, VPL Wan, RAJ Clark, ...
US Patent 10,249,289, 2019
142019
Concatenation artifact detection trained from listeners evaluations
J Vít, J Matoušek
International Conference on Text, Speech and Dialogue, 169-176, 2013
112013
On the analysis of training data for WaveNet-based speech synthesis
J Vít, Z Hanzlíček, J Matoušek
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
102018
LSTM-based speech segmentation for TTS synthesis
Z Hanzlíček, J Vít, D Tihelka
International Conference on Text, Speech, and Dialogue, 361-372, 2019
72019
Unified Language-Independent DNN-Based G2P Converter.
M Juzová, D Tihelka, J Vít
INTERSPEECH, 2085-2089, 2019
72019
Czech speech synthesis with generative neural vocoder
J Vít, Z Hanzlíček, J Matoušek
International Conference on Text, Speech, and Dialogue, 307-315, 2019
62019
Wavenet-based speech synthesis applied to czech
Z Hanzlíček, J Vít, D Tihelka
International Conference on Text, Speech, and Dialogue, 445-452, 2018
52018
Using Auto-Encoder BiLSTM Neural Network for Czech Grapheme-to-Phoneme Conversion
M Jůzová, J Vít
International Conference on Text, Speech, and Dialogue, 91-102, 2019
32019
Grappling with web technologies: The problems of remote speech recording
D Tihelka, M Jůzová, J Vít
International Conference on Speech and Computer, 592-602, 2020
22020
LSTM-Based Speech Segmentation Trained on Different Foreign Languages
Z Hanzlíček, J Vít
International Conference on Text, Speech, and Dialogue, 456-464, 2020
22020
Automatická detekce a vizualizace chyb konkatenační syntézy řeči
J Vít
Západočeská univerzita v Plzni, 2013
22013
Unit-selection speech synthesis adjustments for audiobook-based voices
J Vít, J Matoušek
International Conference on Text, Speech, and Dialogue, 335-342, 2016
12016
KINterestTV-Towards Non–invasive Measure of User Interest While Watching TV
J Leroy, F Rocca, M Mancas, R Ben Madhkour, F Grisard, T Kliegr, ...
International Summer Workshop on Multimodal Interfaces, 179-199, 2013
12013
Speakers Talking Foreign Languages in a Multi-lingual TTS System
Z Hanzlíček, J Vít, M Řezáčková
International Conference on Text, Speech, and Dialogue, 489-498, 2021
2021
Save Your Voice: Voice Banking and TTS for Anyone
D Tihelka, M Řezáčková, M Grůber, Z Hanzlíček, J Vít, J Matoušek
International Speech Communication Association, 2021
2021
Web-Based Speech Synthesis Editor.
M Gruber, J Vít, J Matousek
INTERSPEECH, 3683-3684, 2019
2019
The system can't perform the operation now. Try again later.
Articles 1–20