Cart
Create Account
Sign In
Already purchased this program?
Login to View
This video program is a part of the Premium package:
Transformer-Based Text-To-Speech With Weighted Forced Attention
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Transformer-Based Text-To-Speech With Weighted Forced Attention
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
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
