Search papers, labs, and topics across Lattice.
Guangxi Normal University
2
0
4
0
A new dataset and model achieve a staggering 4.98% symbol error rate for classical music, setting a high bar for audio-to-score transcription in popular music.
Seedance 2.0 leapfrogs existing models by unifying multi-modal inputs (text, image, audio, video) into a single architecture for generating high-quality, longer-duration audio-video content.
