Perturbation-invariant Speech Representation Learning by Online Clustering
Despite success across various tasks, self-supervised speech models face significant challenges in enhancing content-related performance with unlabeled data, requiring substantial computational resources. Meanwhile, learning from clustered discrete units has been shown to facilitate accurate phoneti...
Main Author: | Chang, Heng-Jui |
---|---|
Other Authors: | Glass, James R. |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2024
|
Online Access: | https://hdl.handle.net/1721.1/153784 https://orcid.org/0000-0002-1690-2610 |
Similar Items
-
Learning An Invariant Speech Representation
by: Evangelopoulos, Georgios, et al.
Published: (2015) -
Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction
by: Yusuf Brima, et al.
Published: (2024-02-01) -
On invariance and selectivity in representation learning
by: Anselmi, Fabio, et al.
Published: (2017) -
On Invariance and Selectivity in Representation Learning
by: Anselmi, Fabio, et al.
Published: (2015) -
Unsupervised learning of invariant representations
by: Anselmi, Fabio, et al.
Published: (2018)