Cite
Notes
Only stored in your browser.
Attribution
FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait
ICCV 2025
Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation
arXiv 2021
from 2 papers
Dong Bok Lee
Eunho Yang
Gyeongsu Chae
Sung Ju Hwang
Taekyung Ki