analiza aiqbench
ArtNet advances zero-shot phoneme recognition by adapting the JEPA architecture from vision to audio, leveraging articulatory feature prediction to achieve robustness across unseen languages without direct acoustic-to-symbol mapping. This approach demonstrates significant error rate reductions in cross-lingual tasks, highlighting a promising direction for self-supervised learning models that prioritize universal representations over language-specific variations.
ArtNet: A JEPA-Like Articulatory Predictive Framework for Robust Zero-Shot Phoneme Recognition
arXiv:2606.16595v1 Announce Type: cross Abstract: Zero-shot cross-lingual phoneme recognition is often hindered by the fragility of direct acoustic-to-symbol mapping, which is susceptible to language-specific variations. Echoing joint-embedding predictive architecture (JEPA) work in vision, we propose ArtNet, a framework that explores a structured feature prediction task based on articulatory features to enhance acoustic robustness. Specifically, ArtNet integrates an articulatory predictor, designed to extract universal articulatory representations from self-supervised learning (SSL) features, with a variational information bottleneck (VIB) to suppress language-specific variations. Experiments on seven unseen languages demonstrate that ArtNet, particularly when synergized with the proposed vector-space inventory alignment (VSIA) strategy, significantly outperforms competitive baselines, achieving a 20.56\% relative reduction in phoneme error rate (PER) and 7.01\% in phoneme feature error rate (PFER).
Abstract:Zero-shot cross-lingual phoneme recognition is often hindered by the fragility of direct acoustic-to-symbol mapping, which is susceptible to language-specific variations. Echoing joint-embedding predictive architecture (JEPA) work in vision, we propose ArtNet, a framework that explores a structured feature prediction task based on articulatory features to enhance acoustic robustness. Specifically, ArtNet integrates an articulatory predictor, designed to extract universal articulatory representations from self-supervised learning (SSL) features, with a variational information bottleneck (VIB) to suppress language-specific variations. Experiments on seven unseen languages demonstrate that ArtNet, particularly when synergized with the proposed vector-space inventory alignment (VSIA) strategy, significantly outperforms competitive baselines, achieving a 20.56\% relative reduction in phoneme error rate (PER) and 7.01\% in phoneme feature error rate (PFER).
Sound (cs.SD); Artificial Intelligence (cs.AI)
arXiv:2606.16595 [cs.SD]
(or arXiv:2606.16595v1 [cs.SD] for this version)
https://doi.org/10.48550/arXiv.2606.16595 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
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 · 212 cuvinte
Subiecte conexe
World Models and Yann LeCun’s Bet Against Large Language Models
Quantum Zeitgeist · 17 iul. 2026
Deconfusing Corrigibility
AI Alignment Forum · 17 oct. 2026
Does preservation make sense before we know how to revive?
LessWrong · 15 iun. 2026
Jev: System One models for Prod, not God — with Diogo Almeida, CEO, TypeSafe AI
Latent Space · 21 sept. 2026