Futga: Towards Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation Paper • 2407.20445 • Published Jul 29 • 20
The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation Paper • 2311.10057 • Published Nov 16, 2023 • 1
MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models Paper • 2408.01337 • Published Aug 2 • 11
Facing the Music: Tackling Singing Voice Separation in Cinematic Audio Source Separation Paper • 2408.03588 • Published Aug 7 • 6