Finnish Dialect Identification: The Effect of Audio and Text

Mika Hämäläinen, Khalid Alnajjar, Niko Partanen, Jack Rueter


Abstract
Finnish is a language with multiple dialects that not only differ from each other in terms of accent (pronunciation) but also in terms of morphological forms and lexical choice. We present the first approach to automatically detect the dialect of a speaker based on a dialect transcript and transcript with audio recording in a dataset consisting of 23 different dialects. Our results show that the best accuracy is received by combining both of the modalities, as text only reaches to an overall accuracy of 57%, where as text and audio reach to 85%. Our code, models and data have been released openly on Github and Zenodo.
Anthology ID:
2021.emnlp-main.692
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8777–8783
Language:
URL:
https://aclanthology.org/2021.emnlp-main.692
DOI:
10.18653/v1/2021.emnlp-main.692
Bibkey:
Cite (ACL):
Mika Hämäläinen, Khalid Alnajjar, Niko Partanen, and Jack Rueter. 2021. Finnish Dialect Identification: The Effect of Audio and Text. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8777–8783, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Finnish Dialect Identification: The Effect of Audio and Text (Hämäläinen et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.692.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.692.mp4
Code
 rootroo-ltd/finnishdialectidentification