Beyond Accuracy: Analyzing Dialect Confusion in Automatic Speech-Based Dialect Classification

Lea Fischbach, Alfred Lameli, Lucie Flek


Abstract
Automatic dialect classification is commonly treated as a supervised task with a primary focus on overall accuracy. In this paper, we argue that classification errors and model uncertainty provide valuable insights into dialectal structure and variation. We analyze a speech-based dialect classification model trained on German dialect data from three generations and evaluated across 250 speaker-disjoint splits (median weighted F1=0.42). A systematic confusion analysis shows that misclassifications are largely explained by speaker diversity, dialectal similarity, geographical proximity, and speaker self-assessment. Among these factors, the number of speakers per dialect has the strongest impact on performance, while frequent confusions between closely related dialects reflect inherent linguistic similarity rather than model limitations. Generational analyses further indicate that younger speakers exhibit reduced dialectal distinctiveness, although core dialectal features remain shared across generations. By explicitly modeling classification uncertainty, the proposed approach enables the analysis of dialect transition areas and gradient dialect boundaries. Overall, this work demonstrates that automatic dialect classification can serve not only as a predictive task but also as a tool for dialectological analysis.
Anthology ID:
2026.dialres-1.9
Volume:
Proceedings of the First Workshop on Dialects in NLP — A Resource Perspective
Month:
May
Year:
2026
Address:
Palma de Mallorca
Editors:
Antonis Anastasopoulos, Stella Markantonatou, Angela Ralli, Marcos Zampieri, Stavros Bompolas, Vivian Stamou
Venues:
DialRes | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
93–103
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-dialres-09
DOI:
10.63317/5f65nkr6qreo
Bibkey:
Cite (ACL):
Lea Fischbach, Alfred Lameli, and Lucie Flek. 2026. Beyond Accuracy: Analyzing Dialect Confusion in Automatic Speech-Based Dialect Classification. In Proceedings of the First Workshop on Dialects in NLP — A Resource Perspective, pages 93–103, Palma de Mallorca. Association for Computational Linguistics.
Cite (Informal):
Beyond Accuracy: Analyzing Dialect Confusion in Automatic Speech-Based Dialect Classification (Fischbach et al., DialRes 2026)
Copy Citation: