Search papers, labs, and topics across Lattice.
Singapore University of Technology and Design, University of Antwerp, Queen Mary University of London
4
0
5
19
AI-driven music comparison tools can effectively surface subtle, expert-validated differences by letting users precisely scope comparisons and inspect AI-interpreted features.
Control accent strength in zero-shot TTS with a single model and inference-time weight, outperforming cascaded systems on out-of-domain accents without sacrificing speaker identity.
MERIT achieves unprecedented disentanglement in music representations, enabling precise control over melody, rhythm, and timbre in audio similarity tasks.
Aesthetic quality unlocks better generalization in AI-generated music popularity prediction, beating models trained solely on engagement metrics.
