Detail výsledku
Using machine learning for automatic dialect detection. New methods in Czech dialectology.
This chapter explores machine learning applications in Czech dialectology, focusing specifically in the automatic detection of Czech language dialects. The detector is being developed in the project ‘Language Memory of the Regions of the Czech Republic’ through collaboration amongst dialectology, machine learning, and geoinformatics experts. This software utilizes machine learning methods to identify dialects from audio recordings, drawing from the Archive of Dialect Audio Recordings. The chapter details the archive’s history, cataloging, and recorded language diversity, showcasing the software’s effectiveness in dialect recognition. Results demonstrate substantial improvements over conventional i-vector systems, indicating the promising role of machine learning in Czech dialectology and applied linguistics.
applied dialectology ; Czech dialects ; archive of dialect audio recordings ; automatic dialect detector ; automatic speech recognition
@inbook{BUT201320,
author="{} and Martin {Karafiát} and Oldřich {Plchot}",
title="Using machine learning for automatic dialect detection. New methods in Czech dialectology.",
booktitle="Slovanské dialekty v době digitálních technologií. Nářeční prameny a jejich současné zpracování.",
year="2025",
publisher="Slovanský ústav AV ČR",
address="Praha",
pages="11",
isbn="978-80-86420-99-8",
url="https://www.slu.cas.cz/cs/publikace/slovanske-dialekty-v-dobe-digitalnich-technologii"
}