Salvador Medina — accepted AI-conference papers

2024

PhISANet: Phonetically Informed Speech Animation Network

Salvador Medina, Sarah L. Taylor, Carsten Stoll, Gareth Edwards, Alex Hauptmann, Shinji Watanabe +1

ICASSP 2024accepted

Realistic animation is crucial for immersive and seamless human-avatar interactions as digital avatars become more prevalent. This work presents PhISANet, an encoder-decoder model that realistically animates the face and tongue solely from speech. PhISANet leverages neural audio representations trai…

Cited by 0 Source ↗Scholar ↗

2022

Speech Driven Tongue Animation

Salvador Medina, Denis Tome, Carsten Stoll, Mark Tiede, Kevin Munhall, Alexander G. Hauptmann +1

CVPR 2022poster

Advances in speech driven animation techniques allow the creation of convincing animations for virtual characters solely from audio data. Many existing approaches focus on facial and lip motion and they often do not provide realistic animation of the inner mouth. This paper addresses the problem of…

Cited by 21 PDF ↗Scholar ↗