A character-based analysis of impacts of dialects on end-to-end Norwegian ASR

Phoebe Parsons, Knut Kvale, Torbjørn Svendsen, Giampiero Salvi


Abstract
We present a method for analyzing character errors for use with character-based, end-to-end ASR systems, as used herein for investigating dialectal speech. As end-to-end systems are able to produce novel spellings, there exists a possibility that the spelling variants produced by these systems can capture phonological information beyond the intended target word. We therefore first introduce a way of guaranteeing that similar words and characters are paired during alignment, thus ensuring that any resulting analysis of character errors is founded on sound substitutions. Then, from such a careful character alignment, we find trends in system-generated spellings that align with known phonological features of Norwegian dialects, in particular, “r” and “l” confusability and voiceless stop lenition. Through this analysis, we demonstrate that cues from acoustic dialectal features can influence the output of an end-to-end ASR systems.
Anthology ID:
2023.nodalida-1.47
Volume:
Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)
Month:
May
Year:
2023
Address:
Tórshavn, Faroe Islands
Editors:
Tanel Alumäe, Mark Fishel
Venue:
NoDaLiDa
SIG:
Publisher:
University of Tartu Library
Note:
Pages:
467–476
Language:
URL:
https://aclanthology.org/2023.nodalida-1.47
DOI:
Bibkey:
Cite (ACL):
Phoebe Parsons, Knut Kvale, Torbjørn Svendsen, and Giampiero Salvi. 2023. A character-based analysis of impacts of dialects on end-to-end Norwegian ASR. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 467–476, Tórshavn, Faroe Islands. University of Tartu Library.
Cite (Informal):
A character-based analysis of impacts of dialects on end-to-end Norwegian ASR (Parsons et al., NoDaLiDa 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.nodalida-1.47.pdf