@article{ART003228283},
author={Byong-Kwon Lee},
title={Design and Implementation of an AI-Based Emotion Analysis System through Music and Vocal Separation},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2025},
volume={30},
number={7},
pages={33-39}
TY - JOUR
AU - Byong-Kwon Lee
TI - Design and Implementation of an AI-Based Emotion Analysis System through Music and Vocal Separation
JO - Journal of The Korea Society of Computer and Information
PY - 2025
VL - 30
IS - 7
PB - The Korean Society Of Computer And Information
SP - 33
EP - 39
SN - 1598-849X
AB - The technology for analyzing emotions in music has recently emerged as an important research topic in the field of affective computing. This study designed and implemented an AI-based system for music emotion analysis. Using Spleeter, vocals were separated from the original music, and audio features were extracted with Librosa. The extracted features were then fed into a pre-trained emotion classification model (SVM) to predict emotions at 5-second intervals. The prediction results were visualized through graphs and pie charts, clearly illustrating the temporal flow and distribution of emotions. Experimental results confirmed that both the number of predictions and the average probability are critical variables for emotion determination. In the future, the system can be expanded by refining emotion categories, incorporating instrument-based analysis, and applying deep learning techniques. The significance of this research lies in demonstrating the practicality and scalability of music emotion analysis technology.
KW - Music Emotion Analysis;Music and Vocal Separation;Audio Feature Extraction;Deep Learning;Emotion Visualization
DO -
UR -
ER -
Byong-Kwon Lee. (2025). Design and Implementation of an AI-Based Emotion Analysis System through Music and Vocal Separation. Journal of The Korea Society of Computer and Information, 30(7), 33-39.
Byong-Kwon Lee. 2025, "Design and Implementation of an AI-Based Emotion Analysis System through Music and Vocal Separation", Journal of The Korea Society of Computer and Information, vol.30, no.7 pp.33-39.
Byong-Kwon Lee "Design and Implementation of an AI-Based Emotion Analysis System through Music and Vocal Separation" Journal of The Korea Society of Computer and Information 30.7 pp.33-39 (2025) : 33.
Byong-Kwon Lee. Design and Implementation of an AI-Based Emotion Analysis System through Music and Vocal Separation. 2025; 30(7), 33-39.
Byong-Kwon Lee. "Design and Implementation of an AI-Based Emotion Analysis System through Music and Vocal Separation" Journal of The Korea Society of Computer and Information 30, no.7 (2025) : 33-39.
Byong-Kwon Lee. Design and Implementation of an AI-Based Emotion Analysis System through Music and Vocal Separation. Journal of The Korea Society of Computer and Information, 30(7), 33-39.
Byong-Kwon Lee. Design and Implementation of an AI-Based Emotion Analysis System through Music and Vocal Separation. Journal of The Korea Society of Computer and Information. 2025; 30(7) 33-39.
Byong-Kwon Lee. Design and Implementation of an AI-Based Emotion Analysis System through Music and Vocal Separation. 2025; 30(7), 33-39.
Byong-Kwon Lee. "Design and Implementation of an AI-Based Emotion Analysis System through Music and Vocal Separation" Journal of The Korea Society of Computer and Information 30, no.7 (2025) : 33-39.
