analiza aiqbench
MauBERT advances self-supervised speech learning by integrating articulatory features into multilingual models, achieving superior context-invariant representations across 55 languages with minimal fine-tuning. This approach effectively instills linguistic inductive biases, enabling robust adaptation to unseen languages and casual speech without relying on large-scale labeled datasets.
MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery
arXiv:2512.19612v3 Announce Type: replace 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.
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.
Computation and Language (cs.CL); Audio and Speech Processing (eess.AS)
arXiv:2512.19612 [cs.CL]
(or arXiv:2512.19612v3 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2512.19612 Focus to learn more arXiv-issued DOI via DataCite
https://doi.org/10.18653/v1/2026.acl-long.24 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 215 cuvinte
Subiecte conexe
News
Quantum Computing Report · 7 iun. 2026
Overtly egregiously misaligned trajectories are scored highly.
LessWrong · 24 sept. 2026
Overtly misaligned trajectories score highly in RL.
LessWrong · 24 sept. 2026
Explicit Interaction Architectures for Dynamical Learning: A Controlled Study of Structural Inductive Bias
arXiv · 2 sept. 2026