1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Transformer-Based Text-To-Speech With Weighted Forced Attention

Transformer-Based Text-To-Speech With Weighted Forced Attention

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

This paper investigates state-of-the-art Transformer- and FastSpeech-based high-fidelity neural text-to-speech (TTS) with full-context label input for pitch accent languages. The aim is to realize faster training than conventional Tacotron-based models. I

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

Purchase

Videos in this product

Transformer-Based Text-To-Speech With Weighted Forced Attention

00:14:01

0 views

This paper investigates state-of-the-art Transformer- and FastSpeech-based high-fidelity neural text-to-speech (TTS) with full-context label input for pitch accent languages. The aim is to realize faster training than conventional Tacotron-based models. I