L2 Czech Annotation for Automatic Feedback on Pronunciation

HOLAJ, Richard and Petr POŘÍZKA. L2 Czech Annotation for Automatic Feedback on Pronunciation. In SLOVKO 2021 - NLP, Corpus Linguistics and Interdisciplinarity - October 13–15, 2021. 2021.

Basic information

• Original name: L2 Czech Annotation for Automatic Feedback on Pronunciation
• Authors: HOLAJ, Richard and Petr POŘÍZKA.
• Edition: SLOVKO 2021 - NLP, Corpus Linguistics and Interdisciplinarity - October 13–15, 2021, 2021.

Other information

• Original language: English
• Type of outcome: Presentations at conferences
• Field of Study: 60203 Linguistics
• Country of publisher: Slovakia
• Confidentiality degree: is not subject to a state or trade secret
• Organization unit: Faculty of Arts
• Keywords in English: pronunciation; L2; Czech; machine learning; neural networks; e-learning; annotation; speech recognition; automatic feedback; phonetics
• Tags: International impact, Reviewed

Abstract

In this talk, we provide a brief overview of the current state of pronunciation teaching in e-learning and demonstrate a new approach to building tools for automatic feedback concerning correct pronunciation based on the most frequent or typical errors in speech production made by non-native speakers. We illustrate this in the process of designing annotation for a sound recognition tool to provide feedback on pronunciation. At the end we also present how we have tried to apply this annotation to the tool, what caveats we have found and what our plans are.

Links

• MUNI/IGA/1225/2020, interní kód MU: Name: L2 pronunciation of Czech (linguistic annotation system)

Investor: Masaryk University