1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Mockingjay: Unsupervised Speech Representation Learning With Deep Bidirectional Transformer Encoders

Mockingjay: Unsupervised Speech Representation Learning With Deep Bidirectional Transformer Encoders

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

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

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

Purchase

Videos in this product

Mockingjay: Unsupervised Speech Representation Learning With Deep Bidirectional Transformer Encoders

00:14:59

0 views

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