Soft Clustering Anchors For Selfsupervised Speech Representation Learning In Joint Embedding Prediction Architectures

3 mentions across 1 person

All mentions

Yann LeCun

paper · 2026-01-30

Recommended

“We propose GMM-Anchored JEPA...Code is made available at https://github.com/gioannides/clustering-anchored-jepa.”

GMM-Anchored JEPA Improves Self-Supervised Speech Representation ↗