Matteo Spanio
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper establishes a content-based music information retrieval benchmark for predicting taste from audio using ten frozen audio encoders and compares their performance.
The paper presents aria, a dependency-free runtime for generating text-to-music using Stable Audio 3 on commodity hardware, with a focus on quantization for memory savings and activation steering.
This paper investigates cross-cultural consistency of taste-sound correspondences in AI-generated music using a three-country online experiment.