Abhinaba Roy

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.