self-supervised speech representation learning model
C39888
concept
A self-supervised speech representation learning model is a neural network that learns meaningful audio and speech feature representations directly from large amounts of unlabeled speech data by solving pretext tasks such as masked prediction or contrastive learning.
All labels observed (2)
| Label | Occurrences |
|---|---|
| model of speech events | 1 |
| self-supervised speech representation learning model canonical | 1 |
Instances (2)
| Instance | Via concept surface |
|---|---|
| HuBERT | — |
| SPEAKING model of speech events | model of speech events |