Date/Time: Friday 4/28 from 2-3:30pm
Location: 32-D831
Speaker: Kinan Martin & Canaan Breiss (MIT)
Title: Probing self-supervised speech models for phonetic and phonemic information: a case study in aspiration
Abstract: Textless self-supervised speech models have grown in capabilities in recent years, but the nature of the linguistic information they encode has not yet been thoroughly examined. We evaluate the extent to which these models’ learned representations align with basic representational distinctions made by humans, focusing on a set of phonetic (low-level) and phonemic (more abstract) contrasts instantiated in word-initial stops. We find that robust representations of both phonetic and phonemic distinctions emerge in early layers of these models’ architectures, and are preserved in the principal components of deeper layer representations. Our findings show that speech-trained HuBERT derives a low-noise and low-dimensional sub-space corresponding to abstract phonological distinctions.