Fast Neural Speech Waveform Generative Models With Fully-Connected Layer-Based Upsampling

Fast Neural Speech Waveform Generative Models With Fully-Connected Layer-Based Upsampling

Although end-to-end (E2E) text-to-speech (TTS) models with HiFi-GAN-based neural vocoder (e.g. VITS and JETS) can achieve human-like speech quality with fast inference speed, these models still have room to further improve the inference speed with a CPU for practical implementations because HiFi-GAN...

Full description

Bibliographic Details
Main Authors: Haruki Yamashita, Takuma Okamoto, Ryoichi Takashima, Yamato Ohtani, Tetsuya Takiguchi, Tomoki Toda, Hisashi Kawai
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
End-to-end text-to-speech
fully-connected layer-based upsampling
iSTFTNet
multi-stream HiFi-GAN
neural vocoder
Online Access:https://ieeexplore.ieee.org/document/10438439/

Internet

https://ieeexplore.ieee.org/document/10438439/

Similar Items