English

PiCoGen: Generate Piano Covers with a Two-stage Approach

Sound 2024-07-31 v1 Audio and Speech Processing

Abstract

Cover song generation stands out as a popular way of music making in the music-creative community. In this study, we introduce Piano Cover Generation (PiCoGen), a two-stage approach for automatic cover song generation that transcribes the melody line and chord progression of a song given its audio recording, and then uses the resulting lead sheet as the condition to generate a piano cover in the symbolic domain. This approach is advantageous in that it does not required paired data of covers and their original songs for training. Compared to an existing approach that demands such paired data, our evaluation shows that PiCoGen demonstrates competitive or even superior performance across songs of different musical genres.

Keywords

Cite

@article{arxiv.2407.20883,
  title  = {PiCoGen: Generate Piano Covers with a Two-stage Approach},
  author = {Chih-Pin Tan and Shuen-Huei Guan and Yi-Hsuan Yang},
  journal= {arXiv preprint arXiv:2407.20883},
  year   = {2024}
}

Comments

Published at ICMR 2024 (project page: https://tanchihpin0517.github.io/PiCoGen/)

R2 v1 2026-06-28T17:58:15.844Z