Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction

Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction

Self-supervised learning (SSL) has emerged as a promising paradigm for learning flexible speech representations from <i>unlabeled</i> data. By designing <i>pretext tasks</i> that exploit statistical regularities, SSL models can capture <i>useful</i> representation...

Full description

Bibliographic Details
Main Authors: Yusuf Brima, Ulf Krumnack, Simone Pika, Gunther Heidemann
Format: Article
Language:English
Published: MDPI AG 2024-02-01
Series:Information
Subjects:
acoustic analysis
Barlow Twins
self-supervised learning
invariance
redundancy reduction
speech representation learning
Online Access:https://www.mdpi.com/2078-2489/15/2/114

Internet

https://www.mdpi.com/2078-2489/15/2/114

Similar Items