Multilingual Phonological Feature Recognition with Self-Supervised Speech Models
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Phonological Feature Prediction | FLEURS German | Manner Group F186 | 2 | |
| Phonological Feature Prediction | VoxPopuli German | Manner Group F180.6 | 2 | |
| Phonological Feature Prediction | FLEURS Spanish | Manner Group F193.2 | 2 | |
| Phonological Feature Prediction | VoxPopuli Spanish | Manner Group F190.3 | 2 | |
| Phonological Feature Prediction | CommonVoice Czech (test) | Manner F190.9 | 2 | |
| Phonological Feature Prediction | FLEURS Czech | Manner F189.2 | 2 | |
| Phonological Feature Prediction | VoxPopuli Czech | Manner F1 Score91.8 | 2 | |
| Phonological Feature Prediction | CommonVoice German (test) | Manner F1 Score88.9 | 2 | |
| Phonological Feature Prediction | FLEURS German | Manner F186 | 2 | |
| Phonological Feature Prediction | CommonVoice English (test) | Manner F190.5 | 2 |