Optimum Music: Gesture Controlled, Personalized Music Recommendation System

Abstract

Music plays an important role in everyone’s life since it helps to relax the mind when appropriate music is played. This paper presents a music recommendation system based on the user’s current emotions, activities as well as demographic information such as age, gender, and ethnicity. In addition, the system can be controlled by hand gestures and vocal commands. Unsupervised learning methods in were used to recommend music according to the demographic data and emotions of the user. Finally, the important idea is to recommend music based on all of the user’s data, such as demographics, emotions, and activities. The overall system performance was manually tested and evaluated with a group of individuals, yielding a 70% satisfaction rate for the recommendation; additionally, supporting models such as demographic identification, emotion identification, and hand gesture identification have received a higher proportion of accuracies, contributing to the research’s success. Unlike other systems, ours utilizes all of the user’s information while making music recommendations.