All
All

What are you looking for?

All
Results
Organizations

Quick search

  • Projects supported by TA ČR
  • Excellent projects
  • Projects with the highest public support
  • Current projects

Smart search

  • That is how I find a specific +word
  • That is how I leave the -word out of the results
  • “That is how I can find the whole phrase”

KLAZÁŘ - Classification of speech records

Project goals

- Methodology for detecting topics in speech recordings with minimizing linguistic and dialectical dependence with maximizing of automated procedures. - SW tools for detecting topics in speech records.

Keywords

speech recording

Public support

  • Provider

    Ministry of Defence

  • Programme

  • Call for proposals

  • Main participants

    Vojenský technický ústav, s.p. / odštěpný závod VTÚL a PVO

  • Contest type

    VZ - Public procurement

  • Contract ID

    1801 2 4780

Alternative language

  • Project name in Czech

    KLAZÁŘ - Klasifikace záznamů řeči

  • Annotation in Czech

    - Metodika pro klasifikování témat v záznamech řeči s minimalizováním jazykové či dialektové závislosti s důrazem na maximální využití automatizovaných postupů. - SW nástroje a prostředky pro detekci témat v záznamech řeči.

Scientific branches

  • R&D category

    AP - Applied research

  • OECD FORD - main branch

    20206 - Computer hardware and architecture

  • OECD FORD - secondary branch

    60202 - Specific languages

  • OECD FORD - another secondary branch

    10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

  • AF - Documentation, librarianship, work with information
    AI - Linguistics
    BC - Theory and management systems
    BD - Information theory
    IN - Informatics
    JC - Computer hardware and software

Completed project evaluation

  • Provider evaluation

    U - Uspěl podle zadání (s publikovanými či patentovanými výsledky atd.)

  • Project results evaluation

    The project succeeded according to the assignment – the project has two outputs a) Methodology - Klazář - use of "example based" methods of classification of topics contained in speech records and their basic preprocessing (normalization, noise suppression) and b) SW Klazář Core. The procedures used in the methodology and in the software for solving the problem of detection and classification of speech records are based on the most modern approaches and methods used in a scientific discipline. The achieved results clearly describe that the whole process can be automated while maintaining the requirement for high accuracy of outputs. The methods described in the methodology allow a high degree of flexibility and, if necessary, a change in the language of interest does not change the method of application. By adapting these methods and algorithms, it will make it possible to increase the efficiency of the specialized activity performed in an elementary way.

Solution timeline

  • Realization period - beginning

    Jan 16, 2018

  • Realization period - end

    Dec 31, 2020

  • Project status

    U - Finished project

  • Latest support payment

    Feb 27, 2020

Data delivery to CEP

  • Confidentiality

    C - Předmět řešení projektu podléhá obchodnímu tajemství (§ 504 Občanského zákoníku), ale název projektu, cíle projektu a u ukončeného nebo zastaveného projektu zhodnocení výsledku řešení projektu (údaje P03, P04, P15, P19, P29, PN8) dodané do CEP, jsou upraveny tak, aby byly zveřejnitelné.

  • Data delivery code

    CEP21-MO0-OW-U/02:1

  • Data delivery date

    Jun 24, 2021

Finance

  • Total approved costs

    7,750 thou. CZK

  • Public financial support

    7,750 thou. CZK

  • Other public sources

    0 thou. CZK

  • Non public and foreign sources

    0 thou. CZK

Basic information

Recognised costs

7 750 CZK thou.

Public support

7 750 CZK thou.

100%


Provider

Ministry of Defence

OECD FORD

Computer hardware and architecture

Solution period

16. 01. 2018 - 31. 12. 2020