Sport Style Music Transformation: A GAN-Based Approach Utilizing Musical Features

Abstract

Physical inactivity is one of the major health issues in modern society. Music has shown great potential in enhancing exercise performance and motivation, offering an economical and non-invasive way to improve the exercise experience. However, the number of music tracks available to enhance workout performance is limited, and frequent listening to these tracks can lead to fatigue, diminishing their effectiveness. To address this issue, we explored methods for generating personalized workout music. First, we conducted a detailed analysis of the musical and acoustic features of existing workout music to identify which features are most crucial for enhancing exercise performance and motivation. Based on these features, we developed a GANbased music style transfer model that incorporates these highly relevant workout music features, allowing these characteristics to be embedded into music from different genres. Our results show that our new model generates music that has a higher similarity to workout music compared to the baseline model.