Using machine learning for automatic dialect detection. New methods in Czech dialectology.

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F26%3A0201320" target="_blank" >RIV/00216305:26230/26:0201320 - isvavai.cz</a>

Alternative codes found

RIV/68378092:_____/25:00645993

Result on the web

<a href="https://www.slu.cas.cz/cs/publikace/slovanske-dialekty-v-dobe-digitalnich-technologii" target="_blank" >https://www.slu.cas.cz/cs/publikace/slovanske-dialekty-v-dobe-digitalnich-technologii</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Using machine learning for automatic dialect detection. New methods in Czech dialectology.

Original language description

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.

Czech name

—

Czech description

—

Type

C - Chapter in a specialist book

CEP classification

—

OECD FORD branch

60203 - Linguistics

Project

<a href="/en/project/DH23P03OVV010" target="_blank" >DH23P03OVV010: Language memory of the regions of the Czech Republic. Machine learning methods for preservation, documentation and presentation of the Czech dialects</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Book/collection name

Slovanské dialek­ty v době dig­itál­ních technologií. Nářeční prameny a jejich současné zpracování.

ISBN

978-80-86420-99-8

Number of pages of the result

11

Pages from-to

—

Number of pages of the book

350

Publisher name

Slovanský ústav AV ČR

Place of publication

Praha

UT code for WoS chapter

—