Extracting Unit Embeddings Using Sequence-To-Sequence Acoustic Models For Unit Selection Speech Synthesis

This video program is a part of the Premium package:

Extracting Unit Embeddings Using Sequence-To-Sequence Acoustic Models For Unit Selection Speech Synthesis


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

Extracting Unit Embeddings Using Sequence-To-Sequence Acoustic Models For Unit Selection Speech Synthesis

0 views
  • Share
This paper presents a method of using the intermediate representations between linguistic and acoustic features in a Tacotron model to derive the cost functions for unit selection speech synthesis. By extracting the outputs of the Tacotron encoder, each p
This paper presents a method of using the intermediate representations between linguistic and acoustic features in a Tacotron model to derive the cost functions for unit selection speech synthesis. By extracting the outputs of the Tacotron encoder, each p