Thesis Details

Dynamický dekodér pro rozpoznávání řeči

Master's Thesis Student: Veselý Michal Academic Year: 2016/2017 Supervisor: Schwarz Petr, Ing., Ph.D.
English title
Dynamic Decoder for Speech Recognition
Language
Czech
Abstract

The result of this work is a fully working and significantly optimized implementation of a dynamic decoder. This decoder is based on dynamic recognition network generation and decoding by a modified version of the Token Passing algorithm. The implemented solution provides very similar results to the original static decoder from BSCORE (API of Phonexia company). Compared to BSCORE this implementation offers significant reduction of memory usage. This makes use of more complex language models possible. It also facilitates integration the speech recognition to some mobile devices or dynamic adding of new words to the system.

Keywords

dynamic decoder, language model, acoustic model, speech recognition, recognition network, Token Passing algorithm, n-gram probabilities

Department
Department of Computer Graphics and Multimedia FIT BUT
Degree Programme
Information Technology, Field of Study Intelligent Systems
Files
Status
defended, grade A
Date
22 June 2017
Reviewer
Glembek Ondřej, Ing., Ph.D.
Committee
Zbořil František V., doc. Ing., CSc. (DITS FIT BUT), předseda
Hrubý Martin, Ing., Ph.D. (DITS FIT BUT), člen
Janoušek Vladimír, doc. Ing., Ph.D. (DITS FIT BUT), člen
Jaroš Jiří, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Matyska Luděk, prof. RNDr., CSc. (FI MUNI), člen
Peringer Petr, Dr. Ing. (DITS FIT BUT), člen
Citation
VESELÝ, Michal. Dynamický dekodér pro rozpoznávání řeči. Brno, 2017. Master's Thesis. Brno University of Technology, Faculty of Information Technology. 2017-06-22. Supervised by Schwarz Petr. Available from: https://www.fit.vut.cz/study/thesis/20095/
BibTeX 
@mastersthesis{FITMT20095,
    author = "Michal Vesel\'{y}",
    type = "Master's thesis",
    title = "Dynamick\'{y} dekod\'{e}r pro rozpozn\'{a}v\'{a}n\'{i} \v{r}e\v{c}i",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2017,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/20095/"
}

Theses

Back to top