A Single Self-Supervised Model for Many Speech Modalities Enables Zero-Shot Modality Transfer.

Wei-Ning Hsu Bowen Shi

Published in: CoRR (2022)

Keyphrases

theoretical framework
formal model
computational model
prior knowledge
management system
spoken language
parameter estimation
multi modal
probability distribution
probabilistic model
data sets
object recognition
objective function
statistical model
computational models
reinforcement learning
similarity measure