Automatic feedback on pronunciation and Anophone : a tool for
L2 Czech annotation

D 2023

Automatic feedback on pronunciation and Anophone : a tool for L2 Czech annotation

HOLAJ, Richard a Petr POŘÍZKA

Základní údaje

Originální název

Automatic feedback on pronunciation and Anophone : a tool for L2 Czech annotation

Autoři

HOLAJ, Richard (203 Česká republika, garant, domácí) a Petr POŘÍZKA (203 Česká republika)

Vydání

Prague, Proceedings of the 20th International Congress of Phonetic Sciences, Prague 2023, od s. 2721-2725, 5 s. 2023

Nakladatel

Guarant International

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

60203 Linguistics

Stát vydavatele

Česká republika

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Odkazy

URL URL

Kód RIV

RIV/00216224:14210/23:00132014

Organizační jednotka

Filozofická fakulta

ISBN

978-80-908114-2-3

Klíčová slova anglicky

automatic feedback on pronunciation; speech recognition; annotation; Czech; e-learning

Štítky

rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 18. 2. 2024 14:23, Mgr. et Mgr. Stanislav Hasil

Anotace

V originále

This paper introduces a research project that represents an innovative approach to e-learning applications targeting automatic feedback on the pronunciation of non-native speakers based on computer speech recognition (specifically for Czech). We have collected data from 187 speakers of different pronunciation levels from 36 languages, conducted a pilot project, and developed the first version of an attributive annotation system based on tagging isolated speech sounds. We briefly mention the results of this stage (especially the success rate of the trained model), which led us to change our strategy and move to the next phase of the development of the automatic speech recognition tool. In this article, we present the current and next project phases: the Anophone annotation tool, a new annotation system based on whole-word tagging (two- to four-syllable words). The result is a measurable improvement in both the model and the success rate of speech recognition.

Citovat

HOLAJ, Richard a Petr POŘÍZKA. Automatic feedback on pronunciation and Anophone : a tool for L2 Czech annotation. Online. In Skarnitzl, Radek; Volín, Jan. Proceedings of the 20th International Congress of Phonetic Sciences, Prague 2023. Prague: Guarant International, 2023, s. 2721-2725. ISBN 978-80-908114-2-3.

@inproceedings{2329207,
   author = {Holaj, Richard and Pořízka, Petr},
   address = {Prague},
   booktitle = {Proceedings of the 20th International Congress of Phonetic Sciences, Prague 2023},
   editor = {Skarnitzl, Radek; Volín, Jan},
   keywords = {automatic feedback on pronunciation; speech recognition; annotation; Czech; e-learning},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Prague},
   isbn = {978-80-908114-2-3},
   pages = {2721-2725},
   publisher = {Guarant International},
   title = {Automatic feedback on pronunciation and Anophone : a tool for L2 Czech annotation},
   url = {https://guarant.cz/icphs2023/922.pdf},
   year = {2023}
}

TY  - JOUR
ID  - 2329207
AU  - Holaj, Richard - Pořízka, Petr
PY  - 2023
TI  - Automatic feedback on pronunciation and Anophone : a tool for L2 Czech annotation
PB  - Guarant International
CY  - Prague
SN  - 9788090811423
KW  - automatic feedback on pronunciation
KW  - speech recognition
KW  - annotation
KW  - Czech
KW  - e-learning
UR  - https://guarant.cz/icphs2023/922.pdf
N2  - This paper introduces a research project that represents an innovative approach to e-learning applications targeting automatic feedback on the pronunciation of non-native speakers based on computer speech recognition (specifically for Czech). We have collected data from 187 speakers of different pronunciation levels from 36 languages, conducted a pilot project, and developed the first version of an attributive annotation system based on tagging isolated speech sounds. We briefly mention the results of this stage (especially the success rate of the trained model), which led us to change our strategy and move to the next phase of the development of the automatic speech recognition tool. In this article, we present the current and next project phases: the Anophone annotation tool, a new annotation system based on whole-word tagging (two- to four-syllable words). The result is a measurable improvement in both the model and the success rate of speech recognition.
ER  -

HOLAJ, Richard a Petr POŘÍZKA. Automatic feedback on pronunciation and Anophone : a tool for L2 Czech annotation. Online. In Skarnitzl, Radek; Volín, Jan. \textit{Proceedings of the 20th International Congress of Phonetic Sciences, Prague 2023}. Prague: Guarant International, 2023, s.~2721-2725. ISBN~978-80-908114-2-3.

Podrobný výpis o publikaci