Project Details

Výzkum a vývoj korpusových a hlasových technologií v nové generaci elektronických slovníků

Project Period: 1. 6. 2006 - 31. 12. 2009

Project Type: grant

Code: FT-TA3/006

Agency: Ministry of Industry and Trade of the Czech Republic

Program:

English title
Research and development of corpus and speech technologies in new generation of electronic dictionaries
Type
grant
Keywords

electronic dictionaries, audio corpora, speech recognition, speech synthesis, automatic segmentation, keyword-spotting, text corpora, tagging of corpora, information retrieval

Abstract

The project is focused on the development of a new generation of electronic dictionaries using advanced large language corpora technologies, and on the user interfaces based on speech recognition. The corpus solutions have so far been used in the research community and they are only slowly finding their way to the target applications, the same holds for voice technologies. The proposed project will allow the R&D group of Lingea s.r.o. a shift in state-of-the-art on the Czech as well as international levels. It will thus valorize the funds so far invested into R&D within Lingea. At the cooperating institution - Faculty of Information Technolology, Brno University of Technology, this project will support important research group: Speech@FIT and it will facilitate the transfer of its results to the industrial world.

Team members
Černocký Jan, prof. Dr. Ing. (UPGM FIT VUT) , research leader
Fapšo Michal, Ing. (UPGM FIT VUT) , team leader
Grézl František, Ing., Ph.D. (UPGM FIT VUT) , team leader
Pešán Jan, Ing. (FIT VUT) , team leader
Schwarz Petr, Ing., Ph.D. (UPGM FIT VUT) , team leader
Szőke Igor, Ing., Ph.D. (UPGM FIT VUT) , team leader
Publications

2010

  • ČERNOCKÝ Jan and ŠEVEČKOVÁ Michaela. Korpusové a hlasové technologie v nové generaci elektronických slovníků - závěrečná technická zpráva. Brno: Ministry of Industry and Trade of the Czech Republic, 2010. Detail

2009

  • KOCKMANN Marcel, BURGET Lukáš and ČERNOCKÝ Jan. Brno University of Technology System for Interspeech 2009 Emotion Challenge. In: Proc. Interspeech 2009. Brighton: International Speech Communication Association, 2009, pp. 348-351. ISSN 1990-9772. Detail
  • FAPŠO Michal, SZŐKE Igor and ČERNOCKÝ Jan. Hlasový přístup ke korpusům - experimenty. Brno: Ministry of Industry and Trade of the Czech Republic, 2009. Detail
  • MIKOLOV Tomáš, KOPECKÝ Jiří, BURGET Lukáš, GLEMBEK Ondřej and ČERNOCKÝ Jan. Neural network based language models for highly inflective languages. In: Proc. ICASSP 2009. Taipei: IEEE Signal Processing Society, 2009, p. 4. ISBN 978-1-4244-2354-5. Detail
  • KAŠPAR Michal, PEŠÁN Jan, SZŐKE Igor, CHALUPNÍČEK Kamil and ČERNOCKÝ Jan. Technická zpráva k MPO projektu FT-TA3/006: Práce na Etapě 6: Integrace. Brno: Ministry of Industry and Trade of the Czech Republic, 2009. Detail
  • KAŠPAR Michal, ŠEVEČKOVÁ Michaela, CHALUPNÍČEK Kamil and ČERNOCKÝ Jan. Textové a řečové korpusy. Brno, 2009. Detail

2008

  • KOPECKÝ Jiří, GLEMBEK Ondřej and KARAFIÁT Martin. Advances in Acoustic Modeling for the Recognition of Czech. In: Proc. 11th International Conference on Text, Speech and Dialogue. Lecture Notes in Computer Science, vol. 5246. Berlin: Springer Verlag, 2008, pp. 357-363. ISBN 978-3-540-87390-7. Detail
  • SZŐKE Igor, FAPŠO Michal and ČERNOCKÝ Jan. Hlasový přístup ke korpusům - studie. Brno: Ministry of Industry and Trade of the Czech Republic, 2008. Detail
  • OPARIN Ilya, GLEMBEK Ondřej, BURGET Lukáš and ČERNOCKÝ Jan. Morphological random forests for language modeling of inflectional languages. In: Proc. 2008 IEEE Workshop on Spoken Language Technology. Goa: IEEE Signal Processing Society, 2008, p. 4. ISBN 978-1-4244-3472-5. Detail

2007

  • CHALUPNÍČEK Kamil, ČERNOCKÝ Jan, KOSTKA Martin, PAVELEK Tomáš and VŠIANSKÝ Jan. Automatické hodnocení výslovnosti. Brno: Ministry of Industry and Trade of the Czech Republic, 2007. Detail
  • VESELÝ Karel. Hybrid recognizer of isolated words. In: Proc. 13th Conference STUDENT EEICT 2007. Brno: Faculty of Electrical Engineering and Communication BUT, 2007, pp. 1-3. ISBN 9788021434103. Detail
  • HRDLIČKA Pavel. Isolated word recognition. In: Proc. 13th Conference STUDENT EEICT 2007. Brno: Faculty of Electrical Engineering and Communication BUT, 2007, pp. 1-3. ISBN 9788021434103. Detail
  • GRÉZL František, HRDLIČKA Pavel, VESELÝ Karel, CHALUPNÍČEK Kamil, ČERNOCKÝ Jan, KOSTKA Martin, PAVELEK Tomáš and VŠIANSKÝ Jan. Vyhledávání slovníkových hesel hlasem. Brno: Ministry of Industry and Trade of the Czech Republic, 2007. Detail
Products

2009

  • Module for search in dictionary by voice, software, 2009
    Authors: Szőke Igor, Grézl František, Schwarz Petr, Fapšo Michal Detail
  • Visualization of pronunciation in electronic dictionaries, software, 2009
    Authors: Pešán Jan, Schwarz Petr, Grézl František Detail
Back to top