Cluster Assignments in Soft Targets Shape Speech Representations: Evidence from S-JEPA
S-JEPA, a recent high-performing self-supervised speech model trained with soft Gaussian mixture model (GMM) targets, is compared with counterfactual targets that preserve the most likely cluster and all probability values but change which remaining clusters receive the other probabilities.
Wenxuan He, Yun-Peng Li, Ze-Wei Li et al.
· 0 citations