Článek ve sborníku konference

 
Janda, M.: Grapheme Based Speech Recognition, In: Proceedings of the 18th Conference STUDENT EEICT 2012, Brno, CZ, VUT v Brně, 2012, s. 441-445, ISBN 978-80-214-4460-7
Jazyk publikace:angličtina
Název publikace:Grapheme Based Speech Recognition
Název (cs):Rozpoznávání řeči založené na grafémech
Strany:441-445
Sborník:Proceedings of the 18th Conference STUDENT EEICT 2012
Konference:Student EEICT 2012
Místo vydání:Brno, CZ
Rok:2012
URL:http://www.feec.vutbr.cz/EEICT/2012/sbornik/03doktorskeprojekty/09grafikaamultimedia/02-xjanda16.pdf
ISBN:978-80-214-4460-7
Vydavatel:Vysoké učení technické v Brně
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2012/janda_eeict2012_02-xjanda16.pdf [PDF]
Klíčová slova
speech recognition, LVCSR, ASR, grapheme, phoneme, low-resource languages
Anotace
Článek pojednává o rozpoznávání řeči založené na grafémech, které bylo provedeno pro osm jazyků, jejichž zdroje jsou omezené.
Abstrakt
This article presents the results of grapheme-based speech recognition for eight languages. The need for this approach arises in situation of low resource languages, where obtaining a pronunciation dictionary is time- and cost-consuming or impossible. In such scenarios, usage of grapheme dictionaries is the most simplest and straight-forward. The paper describes the process of automatic generation of pronunciation dictionaries with emphasis on the expansion of numbers. Experiments on GlobalPhone database show that grapheme-based systems have results comparable to the phonemebased ones, especially for phonetic languages.
BibTeX:
@INPROCEEDINGS{
   author = {Miloš Janda},
   title = {Grapheme Based Speech Recognition},
   pages = {441--445},
   booktitle = {Proceedings of the 18th Conference STUDENT EEICT 2012},
   year = {2012},
   location = {Brno, CZ},
   publisher = {Brno University of Technology},
   ISBN = {978-80-214-4460-7},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=10043}
}