Search papers, labs, and topics across Lattice.
3
0
6
SwiftAudio achieves state-of-the-art text-to-audio synthesis with only text captions, challenging the need for paired audio data in model training.
Existing deepfake detectors crumble when faced with realistic, multi-region speech inpainting, leaving a gaping vulnerability that this work begins to address.
An IoT system can monitor student engagement in real-time with 88% accuracy, offering a scalable solution to improve classroom interaction and teaching adaptation.
