1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Aligntts: Efficient Feed-Forward Text-To-Speech System Without Explicit Alignment

Aligntts: Efficient Feed-Forward Text-To-Speech System Without Explicit Alignment

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel. AlignTTS is based on a Feed-Forward Transformer which generates mel-spectrum from a sequence of characters, and the duration of each character

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

Purchase

Videos in this product

Aligntts: Efficient Feed-Forward Text-To-Speech System Without Explicit Alignment

00:12:03

0 views

Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel. AlignTTS is based on a Feed-Forward Transformer which generates mel-spectrum from a sequence of characters, and the duration of each character