2 papers
cs.CL2026
Probing in the Wild: A Case Study of Self-Supervised Speech Representations on Mandarin Sub-dialects with Unsupervised Articulatory Analysis
Shu Shang, Fuliang Weng, Zeqian Hu +1
While self-supervised speech models have achieved strong performance across speech tasks, relatively little is known about how their internal phonetic representations behave under…
cs.SD2026
ArtNet: A JEPA-Like Articulatory Predictive Framework for Robust Zero-Shot Phoneme Recognition
Zeqian Hu, Fuliang Weng, Shu Shang +1
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 j…