Cite
Notes
Only stored in your browser.
Attribution
Social-MAE: A Transformer-Based Multimodal Autoencoder for Face and Voice
arXiv 2025
Deep learning-based stereo camera multi-video synchronization
arXiv 2023
The Emotional Voices Database: Towards Controlling the Emotion Dimension in Voice Generation Systems
arXiv 2018
from 3 papers
Kevin El Haddad
Adaeze Adigwe
François Cresson
Hugo Bohy
Minh Tran
Mohammad Soleymani
Nicolas Boizard
Noé Tits
Sarah Ostadabbas
Thierry Ravet