Year: 2023
Type: preprint
Abstract: We are investigating the broader concept of using AI-based generative music systems to generate training data for Music Information Retrieval (MIR) tasks. To kick off this line of work, we ran an initial experiment in which we trained a genre classifier on a fully artificial music dataset created with MusicGen. We constructed over 50 000 genre- conditioned textual descriptions and generated a collection of music excerpts that covers five musical genres. Our preliminary results show that the proposed model can learn genre-specific characteristics from artificial music tracks that generalise well to real-world music recordings.
Source: arXiv (Cornell University)
Institution: University of Piraeus
Language: English
Topic: Music and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4388748381