Probing self-supervised speech models for phonetic and phonemic information: a case study in aspiration
This work provides insights into the linguistic capabilities of speech models, which is incremental for researchers in speech processing and computational linguistics.
The study investigated how self-supervised speech models encode phonetic and phonemic information, finding that robust representations of these distinctions emerge in early layers and are preserved in deeper layers, with HuBERT deriving a low-noise, low-dimensional subspace for abstract phonological distinctions.
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 analyses suggest two sources for this success: some can only be explained by the optimization of the models on speech data, while some can be attributed to these models' high-dimensional architectures. Our findings show that speech-trained HuBERT derives a low-noise and low-dimensional subspace corresponding to abstract phonological distinctions.