English

Multilingual Phonological Feature Recognition with Self-Supervised Speech Models

Computation and Language 2026-05-26 v1

Abstract

Phonological features provide a language-general and linguistically grounded representation of speech. We present PhonoQ-2.0, a multilingual frame-level phonological feature recognizer built on self-supervised speech models. The system directly predicts a structured 22-dimensional feature vector per frame encoding manner, vowel quality, place, and voicing, instead of deriving features from phoneme outputs. To ensure phonologically coherent predictions, we introduce a manner-conditioned gating mechanism that activates valid feature groups. Evaluated across multiple languages and corpora, PhonoQ-2.0 achieves an average macro-F1 of 91.3% in-domain and 88.9% out-of-domain. Compared to a strong CTC phoneme baseline, it delivers consistent gains of +8.8 F1 in-domain and +8.6 out-of-domain on average. In unseen-language evaluation, PhonoQ-2.0 improves macro-F1 from 66.9% to 73.6% (+6.7 on average), with gains of up to +10.8 points.

Keywords

Cite

@article{arxiv.2605.25596,
  title  = {Multilingual Phonological Feature Recognition with Self-Supervised Speech Models},
  author = {Abner Hernandez and Tomás Arias-Vergara and Daiqi Liu and Andreas Maier and Paula Andrea Pérez-Toro},
  journal= {arXiv preprint arXiv:2605.25596},
  year   = {2026}
}

Comments

Submitted to Interspeech 2026