Search papers, labs, and topics across Lattice.
3
0
6
Achieving an unprecedented equal error rate of 0.88% in audio deepfake detection, this model sets a new benchmark for robustness against sophisticated voice synthesis attacks.
dOPSD leverages a model's own decoding process to provide on-policy supervision, leading to substantial gains in reasoning performance without external labels.
VieSpeaker demonstrates that you can build a robust speaker recognition dataset without relying on visual cues, unlocking new possibilities for under-resourced languages.
