Gediminas Navickas
Department: Image and Signal Analysis Group
Position: Projects Specialist, Lecturer
Address: Akademijos st. 4, room 616, Vilnius
Phone: (+370 5) 210 9308
E-mail:
Research Work
- Automatic Lithuanian speech recognition,
- Lithuanian speech synthesis,
- Deep Neural Networks, especially LSTMs,
- Speech signal processing,
- Speech recognition methods and algorithms,
- Speech interface applications in different fields,
- Robotics,
- ICT applications in different fields.
Scientific publications
Recent publications:
Gediminas Navickas, G. A. Melnik-Leroy. (2023) Can Better Perception Become a Disadvantage? Synthetic Speech Perception in Congenitally Blind Users. Proc. INTERSPEECH 2023, 1100-1103, doi: 10.21437/Interspeech.2023-2013. Online: <https://www.isca-speech.org/archive/pdfs/interspeech_2023/melnikleroy23_interspeech.pdf>
Gediminas Navickas, G. A. Melnik-Leroy. Evaluating Synthesized Speech: The Cognitive Approach // DAMSS 2022 : 13th international workshop on „Data analysis methods for software systems“, Druskininkai, Lithuania, December 1–3, 2022 : [abstract book]. Vilnius : Vilnius University Press, 2022. ISBN 9786090707944 (print), ISBN 9786090707951 (digital PDF), p. 68. Online: <https://www.mii.lt/damss/files/damss_2022.pdf>.
G. Navickas, G. A. Melnik-Leroy. "Do we all perceive synthetic speech in the same way? Testing congenitally blind versus sighted listeners" // Proceedings of the 44th Annual Conference of the Cognitive Science Society, Toronto, Canada, 2022, August 1. p. 3864
Gediminas Navickas, Gerda Ana Melnik-Leroy, Povilas Treigys. Measuring the Quality of Synthetic Speech // DAMSS 2021 : 12th international workshop on „Data analysis methods for software systems“, Druskininkai, Lithuania, December 2–4, 2021 : [abstract book]. Vilnius : Vilnius University Press, 2021. ISBN 9786090706732 (print), ISBN 9786090706749 (digital PDF), p. 54. Online: <https://www.journals.vu.lt/proceedings/article/view/25028/24294>.
Gediminas Navickas. Lithuanian Speech Synthesis Using Deep Neural Networks // DAMSS 2019 : 11th international workshop on "Data analysis methods for software systems", Druskininkai, Lithuania, November 28 - 30, 2019 : [abstract book]. Vilnius : Vilnius University Press, 2019. ISBN 9786090703243 (print), ISBN 9786090703250 (digital PDF), p. 58. Online: <https://www.mii.lt/datamss/files/DAMSS_2019.pdf>.
Navickas, Gediminas; Korvel, Gražina; Bernatavičienė, Jolita. Overview of speech synthesis using LSTM neural networks // Computer data analysis and modeling: stochastics and data science : proceedings of the XII international conference, Minsk, September 18-22, 2019: Proceedings of the XII International Conference, Minsk Spet. 18-22, 2019. Minsk : Belarusian State University, 2019. ISBN 9789855668115. p. 257-261.
Telksnys, Adolfas Laimutis; Navickas, Gediminas. Žmonių ir kompiuterių sąveika šnekant // Kompiuterininkų dienos - 2015 / Lietuvos kompiuterininkų sąjunga. Vilnius : Žara, 2015. ISBN 9789986343134. p. 185-193. Online: <http://www.liks.lt/kodi2015/KoDi-2015-maketas-spaudai.pdf>.
Presentations at conferences
Gediminas Navickas, Gražina Korvel. Universality, diversity and idiosyncrasy in language technology (UniDive) // 14th international workshop on Data analysis methods for software systems, November 30 – December 2, 2023, Druskininkai, Lithuania.
G. Navickas, G. A. Melnik-Leroy. „Kognityvinių metodų taikymas sintezuotos šnekos kokybei vertinti“ // XXI mokslinė kompiuterininkų konferencija „Kompiuterininkų dienos 2023“, 2023 m. rugsėjo 28 d., Vilniaus universiteto Kauno fakultetas.
G. Navickas, G. A. Melnik-Leroy. Can Better Perception Become a Disadvantage? Synthetic Speech Perception in Congenitally Blind Users // 24th INTERSPEECH Conference, 20-24 August 2023, Dublin, Ireland.
Gediminas Navickas, G. A. Melnik-Leroy. Evaluating Synthesized Speech: The Cognitive Approach // 13th international workshop on Data analysis methods for software systems, December 1–3, 2022, Druskininkai, Lithuania.
G. Navickas, G. A. Melnik-Leroy. "Do we all perceive synthetic speech in the same way? Testing blind versus sighted listeners" // CogSci 2022. The 44th Annual Meeting of the Cognitive Science Society "Cognitive Diversity". Toronto, Canada, 2022, August 27-30.
G. Navickas, G. A. Melnik-Leroy, P. Treigys. „Measuring the Quality of Synthetic Speech“ // 12th International Workshop on Data Analysis Methods for Software Systems, December 2 – 4, 2021, Druskininkai, Lithuania.
G. Navickas. "Creating, managing and sharing language data: existing practices and challenges" // Trečiasis Europos kalbų išteklių koordinavimo (ELRC) seminaras Lietuvoje, December 1, 2021, Online.
G. Navickas. „Lietuvių šneka valdomos technologijos“ // Vilnius University Innovation Day ,,INNODAY", November 19, 2021, Vilnius University.
G. Navickas, G. A. Melnik-Leroy, P. Treigys. „Do we all perceive synthetic speech in the same way? Testing blind versus sighted listeners“ // XX scientific conference „Computer Days / Kompiuterininkų dienos 2021“, September 23-24, 2021, Klaipeda university
G. Navickas. „Lietuvių šneka mobiliosiose technologijose“ // Kalbų vakaras, March 24, 2021, Online.
G. Navickas. "Lithuanian Speech Synthesis Using Deep Neural Networks" // 11th International Workshop on Data Analysis Methods for Software Systems, November 28-30, 2019, Druskininkai, Lithuania.
G. Navickas, G. Tamulevičius. Investigation of Neural Networks for Lithuanian Speech Synthesis // The 7th IEEE Workshop on Advances in Information, Electronic and Electrical Engineering, Liepaja, Latvia, November 15-16, 2019.
G. Navickas, G. Korvel, J. Bernatavičienė. Overview of Speech Synthesis Using LSTM Neural Networks // 12th international conference “Computer data analysis and modeling: theoretical and applied stochastics”, Minsk, September 18-22, Minsk:BSU, 2019.
Scientific and other projects
COST action CA21167 „UniDive: Universality, diversity and idiosyncrasy in language technology“.
2022–2026. Position: MC Member, member of working groups: WG1: Corpus annotation, WG3: Multilingual and cross-lingual language technology.
COST action CA18231 „Multi3Generation: Multi-task, Multilingual, Multi-modal Language Generation“.
2019–2023. Position: MC Member, member of working group WG2: Efficient Machine Learning algorithms, methods, and applications to language generation.
EU Structural Funds project LIEPA 2 - Development of the Services controlled by the Lithuanian Speech,
2017-2020. Position: Expert, Chief Specialist.
EU Structural Funds project LIEPA - Services controlled by the Lithuanian Speech,
2013-2015. Position: Expert, Chief Specialist.