4 papers
Investigating Modality Contribution in Audio LLMs for Music
Giovana Morais, Magdalena Fuentes
Audio Large Language Models (Audio LLMs) enable human-like conversation about music, yet it is unclear if they are truly listening to the audio or just using textual reasoning, as…
Learning from Silence and Noise for Visual Sound Source Localization
Xavier Juanola, Giovana Morais, Magdalena Fuentes +1
Visual sound source localization is a fundamental perception task that aims to detect the location of sounding sources in a video given its audio. Despite recent progress, we ident…
Musical Source Separation of Brazilian Percussion
Richa Namballa, Giovana Morais, Magdalena Fuentes
Musical source separation (MSS) has recently seen a big breakthrough in separating instruments from a mixture in the context of Western music, but research on non-Western instrumen…
Skip That Beat: Augmenting Meter Tracking Models for Underrepresented Time Signatures
Giovana Morais, Brian McFee, Magdalena Fuentes
Beat and downbeat tracking models are predominantly developed using datasets with music in 4/4 meter, which decreases their generalization to repertories in other time signatures,…