{"ID":2826365,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.19612","arxiv_id":"2512.19612","title":"MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery","abstract":"This paper introduces MauBERT, a multilingual extension of HuBERT that leverages articulatory features for robust cross-lingual phonetic representation learning. We continue HuBERT pre-training with supervision based on a phonetic-to-articulatory feature mapping in 55 languages. Our models learn from multilingual data to predict articulatory features or phones, resulting in language-independent representations that capture multilingual phonetic properties. Through comprehensive ABX discriminability testing, we show MauBERT models produce more context-invariant representations than state-of-the-art multilingual self-supervised learning models. Additionally, the models effectively adapt to unseen languages and casual speech with minimal self-supervised fine-tuning (10 hours of speech). This establishes an effective approach for instilling linguistic inductive biases in self-supervised speech models.","short_abstract":"This paper introduces MauBERT, a multilingual extension of HuBERT that leverages articulatory features for robust cross-lingual phonetic representation learning. We continue HuBERT pre-training with supervision based on a phonetic-to-articulatory feature mapping in 55 languages. Our models learn from multilingual data...","url_abs":"https://arxiv.org/abs/2512.19612","url_pdf":"https://arxiv.org/pdf/2512.19612v1","authors":"[\"Angelo Ortiz Tandazo\",\"Manel Khentout\",\"Youssef Benchekroun\",\"Thomas Hueber\",\"Emmanuel Dupoux\"]","published":"2025-12-22T17:47:49Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"eess.AS\"]","methods":"[]","has_code":false}