1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Fully-Hierarchical Fine-Grained Prosody Modeling For Interpretable Speech Synthesis

Fully-Hierarchical Fine-Grained Prosody Modeling For Interpretable Speech Synthesis

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

This paper proposes a hierarchical, fine-grained and interpretable latent variable model for prosody based on the Tacotron 2 text-to-speech model. It achieves multi-resolution modeling of prosody by conditioning finer level representations on coarser leve

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

Purchase

Videos in this product

Fully-Hierarchical Fine-Grained Prosody Modeling For Interpretable Speech Synthesis

00:15:13

0 views

This paper proposes a hierarchical, fine-grained and interpretable latent variable model for prosody based on the Tacotron 2 text-to-speech model. It achieves multi-resolution modeling of prosody by conditioning finer level representations on coarser leve