Ing. František Kynych

Ing. František Kynych
Institute of Information Technology and Electronics (ITE): Internal postgraduate student

E-mail:: frantisek.kynych@tul.cz
Office:: A02023
Tel.:: +420 48535 3037
STAG:: STAG profile

Consulting Hours: by appointment
Specialisation: Speaker Recognition, Speaker Diarization, Deep Learning, Machine Learning
Achieved education: 2020 Ing.

Publications

KYNYCH, F. et al. A lightweight approach to real-time speaker diarization: from audio toward audio-visual data streams Eurasip Journal on Audio, Speech, and Music Processing Springer, 2024, vol. 2024, issue 1. P. neuvedeny (16 stran). ISSN: 1687-4722.
KYNYCH, F., ČERVA, P. , and ŽĎÁNSKÝ, J. Systém pro online diarizaci mluvčích v audiovizuálních datových proudech [software].
MATĚJŮ, L. et al. Combining Multilingual Resources and Models to Develop State-of-the-Art E2E ASR for Swedish Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH Dublin: ISCA, 2023 P. 3252 – 3256. ISSN: 2308-457X.
KYNYCH, F., ŽĎÁNSKÝ, J., ČERVA, P. , and MATĚJŮ, L. Online Speaker Diarization Using Optimized SE-ResNet Architecture Lecture Notes in Computer Science Německo: Springer, 2023 P. 176 – 187. ISBN: 978-303140497-9, ISSN: 03029743.
MATĚJŮ, L. et al. Overlapped Speech Detection in Broadcast Streams Using X-vectors Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH Jižní Korea: ISCA, 2022 P. 4606 – 4610. ISSN: 2308-457X.
všechny publikace
ČERVA, P. et al. Identification of Scandinavian Languages from Speech Using Bottleneck Features and X-vectors Lecture Notes in Computer Science Switzerland: Springer Nature Switzerland AG, 2021 P. 371 – 381. ISBN: 978-303083526-2, ISSN: 0302-9743.
MATĚJŮ, L. et al. Using X-vectors for Speech Activity Detection in Broadcast Streams Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH ISCA, 2021 P. 4161 – 4165. ISBN: 978-171383690-2, ISSN: 2308-457X.

Topics of Student work

Identification of authorship using language models, ITE, 2023
Natural language interface for large SQL databases, ITE, 2023
Using diffusion models to embed QR code in images, ITE, 2023

Správa studentských prací a projektů

Show all staff Co-workers at ITE

Ing. František Kynych

Set filter to set related news and events to your interest