Disentangled Speech Embeddings Using Cross-Modal Self-Supervision.

Arsha Nagrani Joon Son Chung Samuel Albanie Andrew Zisserman

Published in: ICASSP (2020)

Keyphrases

cross modal
multi modal
perceptual information
visual recognition
multimedia retrieval
image retrieval
visual similarity
multimedia databases
low dimensional
active learning
dimensionality reduction
visual data
visual information
learning tasks
high level
high dimensional data
image data
object recognition