# Live Vocal Extraction from K-pop Performances

## TL;DR

This paper introduces a methodology for automatically extracting live vocals from K-pop performances by removing pre-recorded vocals and instrumentals, enabling new analysis of live singing in a popular music genre.

## Contribution

It proposes the task of live vocal separation and develops a method combining source separation, cross-correlation, and amplitude scaling for this purpose.

## Key findings

- Initial demonstration of live vocal extraction feasibility
- Framework for future research in live performance audio processing
- Foundation for improved live vocal analysis tools

## 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.