Papers by Manel Khentout
MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery (2026.acl-long)
Copied to clipboard
| Challenge: | MauBERT models learn from multilingual data to predict articulatory features or phones, resulting in language-independent phonetic representations. |
| Approach: | They introduce a multilingual extension of HuBERT that leverages articulatory features for robust cross-lingual phonetic representation learning. |
| Outcome: | The proposed model can predict phonetic features in 55 languages with minimal fine-tuning (10 hours of speech) it is more context-invariant than state-of-the-art models and adapts to unseen languages and casual speech with minimal self-supervised fine- tuning (10 hours) |