1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Unsupervised Style And Content Separation By Minimizing Mutual Information For Speech Synthesis

Unsupervised Style And Content Separation By Minimizing Mutual Information For Speech Synthesis

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

We present a method to generate speech from input text and a style vector that is extracted from a reference speech signal in an unsupervised manner, i.e., no style annotation, such as speaker information, is required. Existing unsupervised methods, durin

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

Purchase

Videos in this product

Unsupervised Style And Content Separation By Minimizing Mutual Information For Speech Synthesis

00:15:44

0 views

We present a method to generate speech from input text and a style vector that is extracted from a reference speech signal in an unsupervised manner, i.e., no style annotation, such as speaker information, is required. Existing unsupervised methods, durin