Pol Buitrago

Audio-driven synthetic lip movements alone can bootstrap audiovisual speech recognition baselines and slash word error rates by up to 16.2% when used as augmentation.

Language mismatch is the primary culprit behind performance degradation in cross-lingual speaker verification, overshadowing speaker variability.

Paralinguistic speech tasks aren't as language-agnostic as we thought: cross-lingual transfer patterns reveal systematic language dependencies.

Unlock AV speech recognition for any language, even with zero labeled video data, by training on synthetically generated talking-head videos.