What Do Neural Speech Models Know About Phonology? Evidence from Structured Phoneme Confusions

Eli Stafford, Aimée Lahaussois, Guillaume Wisniewski


Abstract
ASR errors are typically analysed at the phoneme level, treating phonemes as atomic symbols. In this work, we instead adopt a featural representation of phonemes, grounded in phonological theory, which models speech sounds as structured bundles of distinctive articulatory and acoustic properties. This perspective allows us to analyse recognition errors at a finer granularity and to investigate whether certain phonological features are more vulnerable than others. Across multiple languages, we show that phoneme confusions are strongly structured in phonological feature space: errors are predominantly local and exhibit systematic asymmetries that reveal a small set of weakly modelled features. These findings have direct implications both for the design and diagnosis of ASR systems and for cognitive models of human speech perception, where similar feature-level asymmetries have long been observed.
Anthology ID:
2026.findings-acl.1288
Volume:
Findings of the Association for Computational Linguistics: ACL 2026
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
25860–25873
Language:
URL:
https://aclanthology.org/2026.findings-acl.1288/
DOI:
Bibkey:
Cite (ACL):
Eli Stafford, Aimée Lahaussois, and Guillaume Wisniewski. 2026. What Do Neural Speech Models Know About Phonology? Evidence from Structured Phoneme Confusions. In Findings of the Association for Computational Linguistics: ACL 2026, pages 25860–25873, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
What Do Neural Speech Models Know About Phonology? Evidence from Structured Phoneme Confusions (Stafford et al., Findings 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.findings-acl.1288.pdf
Checklist:
 2026.findings-acl.1288.checklist.pdf