Live Vocal Extraction from K-pop Performances
Audio and Speech Processing
2025-08-29 v1 Sound
Signal Processing
Abstract
K-pop's global success is fueled by its dynamic performances and vibrant fan engagement. Inspired by K-pop fan culture, we propose a methodology for automatically extracting live vocals from performances. We use a combination of source separation, cross-correlation, and amplitude scaling to automatically remove pre-recorded vocals and instrumentals from a live performance. Our preliminary work introduces the task of live vocal separation and provides a foundation for future research in this topic.
Cite
@article{arxiv.2508.20273,
title = {Live Vocal Extraction from K-pop Performances},
author = {Yujin Kim and Richa Namballa and Magdalena Fuentes},
journal= {arXiv preprint arXiv:2508.20273},
year = {2025}
}
Comments
2 pages + references, 1 figure, Extended Abstracts for the Late-Breaking Demo Session of the 26th International Society for Music Information Retrieval Conference