Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
5
0
5
2
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.
Efficient attention mechanisms like RetNet and LightNet can speed up Speech Emotion Recognition by an order of magnitude, but at the cost of some accuracy compared to standard self-attention.
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.