Mockingjay: Unsupervised Speech Representation Learning With Deep Bidirectional Transformer Encoders

This video program is a part of the Premium package:

Mockingjay: Unsupervised Speech Representation Learning With Deep Bidirectional Transformer Encoders


  • IEEE MemberUS $11.00
  • Society MemberUS $0.00
  • IEEE Student MemberUS $11.00
  • Non-IEEE MemberUS $15.00
Purchase

Mockingjay: Unsupervised Speech Representation Learning With Deep Bidirectional Transformer Encoders

0 views
  • Share
Create Account or Sign In to post comments
We present Mockingjay as a new speech representation learning approach, where bidirectional Transformer encoders are pre-trained on a large amount of unlabeled speech. Previous speech representation methods learn through conditioning on past frames and pr
We present Mockingjay as a new speech representation learning approach, where bidirectional Transformer encoders are pre-trained on a large amount of unlabeled speech. Previous speech representation methods learn through conditioning on past frames and pr