Skip to content

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

GLaS-JEPA: Gaussian-Regularized Speech SSL without Engineered Prediction Targets

GLaS-JEPA is presented, a framework that directly predicts the current encoder's continuous representations at masked positions, without contrastive learning, discrete targets, or separate EMA target encoders, and prevents representation collapse using SIGReg representation-space regularization.

G. Botté, Séverin Baroudi, Samir Sadok et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.