4 papers submitted & accepted at #ACL2026 š So grateful to work alongside & learn from amazing minds, pushing the boundaries of speech technologies, machine learning, and computational linguistics. See you in San Diego!
Thanks a lot for the interest in our work! Here's the recording for people who missed the seminar: youtu.be/DtFYKvNo9IQ
Huge thanks for my wonderful coauthors, Eunjung and Cheol-jun, and my two favorite Davids, Mortensen š and Harwath š¤ ā best advisors I could ask for š Can't wait to see what we cook up next! š
š§µ Together, both papers take a step beyond the usual "what info do S3Ms encode" probing paradigm. We aim to answer how is that info actually encoded geometrically? Come see for yourself Thursday! š
Slides: docs.google.com/presentation...
š Paper 2 (submitted to IS): "Self-Supervised Speech Models Encode Phonetic Context via Position-dependent Orthogonal Subspaces"
We further show how sequences of phone(me)s can be encoded, i.e., contextualize, in a single S3M frame.
arxiv.org/abs/2603.12642
š Paper 1 (submitted to Jan ARR):
"[b] = [d] ā [t] + [p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic"
We show how phone(me)s are encoded in S3Ms: as a linear combination of phonological feature vectors.
arxiv.org/abs/2602.18899