Disentangling Linguistic and Paralinguistic Information with Routed Sparse Autoencoders
Self-supervised speech encoders contain linguistic and paralinguistic information in a shared, entangled representation space. We combine a TopK sparse autoencoder with route-specific supervision and cross-factor adversaries.
By Beimnet Bekele Guta, Xiaoyu Yang, Guangzhi Sun, Philip C. WoodlandarXiv - cs.CL (NLP)
Read the full story
Originally published by arXiv - cs.CL (NLP) on Oct 9, 2026.
Comments
Sign in to join the discussion.