Published September 20, 2023 | Version v1
Preprint Open

Investigating Personalization Methods in Text to Music Generation

  • 1. National and Kapodistrian University of Athens
  • 2. Athena Research and Innovation Center in Information Communication and Knowledge Technologies

Description

In this work, we investigate the personalization of text-to-music diffusion models in a few-shot setting. Motivated by recent advances in the computer vision domain, we are the first to explore the combination of pre-trained text-to-audio diffusers with two established personalization methods. We experiment with the effect of audio-specific data augmentation on the overall system performance and assess different training strategies. For evaluation, we construct a novel dataset with prompts and music clips. We consider both embedding-based and music-specific metrics for quantitative evaluation, as well as a user study for qualitative evaluation. Our analysis shows that similarity metrics are in accordance with user preferences and that current personalization approaches tend to learn rhythmic music constructs more easily than melody. The code, dataset, and example material of this study are open to the research community.

Files

2309.11140.pdf

Files (618.1 kB)

Name Size Download all
md5:a145754f4c185ec7d3354d12dfe25c03
618.1 kB Preview Download

Additional details

Software