Showing 2026Show all
3 papers · 1 filter
eess.AS2026
Enhancing Pathological Speech through Articulatory Bottlenecks
Ailín Pollio San Pedro, Olivier Perrotin, Thomas Hueber
Dysarthric speech reconstruction (DSR) typically relies on linguistic or phonetic representations extracted from impaired speech to generate a more intelligible waveform. We invest…
eess.AS2026
GLaS-JEPA: Gaussian-Regularized Speech SSL without Engineered Prediction Targets
Gaspard Botté, Séverin Baroudi, Samir Sadok +5
Speech self-supervised learning aims to learn general-purpose representations for downstream speech tasks. However, current approaches rely on complex, carefully designed predictio…
cs.CL2026
From Tokens to Faces: Investigating Discrete Speech Representations for 3D Facial Animation
Pedro Correa, Olivier Perrotin, Samir Sadok +2
The choice of speech representation is critical in speech-driven 3D facial animation. Representations differ in what they encode: SSL features emphasize segmental and semantic cues…