Song Recommendation Application Using Speech Emotion Recognition

This research was conducted to facilitate the interaction between radio broadcasters and listeners during song request process. triggered by difficulty of in monitoring requests from listeners. The system is made accommodate all application produced this study uses speech emotion recognition technology based on a person's mood obtained spoken words. can change voice into one categories: neutral, angry, sad, afraid. k-Nearest Neighbor method used get recommendations for recommended titles looking closeness value listener's availability playlists. kNN because suitable user-based collaborative problems. will recommend three songs which then be offered broadcasters. Based tests listeners, has recommending according mood, text message, searching songs, details that have been requested. Functional test carried out received 100 components succeeded as expected.