Can MusicGen Create Training Data for MIR Tasks?

Nadine Kroher, Helena Cuesta, Aggelos Pikrakis
11/15/2023
cs.SDcs.AIeess.AS

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

An Autoethnographic Exploration of XAI in Algorithmic Composition

87% match2023

Exploring Variational Auto-Encoder Architectures, Configurations, and Datasets for Generative Music Explainable AI

85% match1 repo142023

Enhancing Music Genre Classification through Multi-Algorithm Analysis and User-Friendly Visualization

85% match2024

Assisted Sound Sample Generation with Musical Conditioning in Adversarial Auto-Encoders

84% match2 repos112019

MuPT: A Generative Symbolic Music Pretrained Transformer

84% match2024

CompLex: Music Theory Lexicon Constructed by Autonomous Agents for Automatic Music Generation

84% match2025

Cite this paper

@article{kroher2023musicgen,
  title  = {Can MusicGen Create Training Data for MIR Tasks?},
  author = {Nadine Kroher and Helena Cuesta and Aggelos Pikrakis},
  year   = {2023},
  eprint = {2311.09094},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.09094v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.09094.svg)](https://codeofpaper.com/paper/2311.09094)

Discussion