mlsanityData to 13 Oct 2026

Can MusicGen Create Training Data for MIR Tasks?

arXiv 2311.09094 ↗First posted 15 Nov 2023cs.SD cs.AI eess.AScited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 6 of its 9 references that are in the map. First posted on arXiv 15 Nov 2023.

Builds on

6 of 9 references.

References · 6

  1. 2023Simple and Controllable Music Generationcited by 484
  2. 2023MusicLM: Generating Music From Textcited by 445
  3. 2020A Brief Review of Domain Adaptationcited by 287
  4. 2021Efficient Training of Audio Transformers with Patchoutcited by 223
  5. 2023JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Modelscited by 41
  6. 2023Audio Embeddings as Teachers for Music Classificationcited by 5

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Towards Training Music Taggers on Synthetic Datacited by 1