Multilingual Phonological Feature Recognition with Self-Supervised Speech Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914599317536768 |
|---|---|
| author | Hernandez, Abner Arias-Vergara, Tomás Liu, Daiqi Maier, Andreas Pérez-Toro, Paula Andrea |
| author_facet | Hernandez, Abner Arias-Vergara, Tomás Liu, Daiqi Maier, Andreas Pérez-Toro, Paula Andrea |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_25596 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multilingual Phonological Feature Recognition with Self-Supervised Speech Models Hernandez, Abner Arias-Vergara, Tomás Liu, Daiqi Maier, Andreas Pérez-Toro, Paula Andrea Computation and Language 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. |
| title | Multilingual Phonological Feature Recognition with Self-Supervised Speech Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.25596 |