Publication Date: 2023/06/15
Abstract: Songs have always been a popular medium for communicating and understanding human emotions. Reliable emotion-based categorization systems can be quite helpful to us in understanding their relevance. However, the results of the study on motion-based music classification have not been the greatest. Here, we introduce EMP, a cross-platform emotional music player that recommends songs based on the user's feelings at the time. EMP provides intelligent mood-based music suggestions by incorporating emotion context reasoning abilities into our adaptive music recommendation engine. Our music player is composed of three modules: the emotion module, the random music player module, and the queue-based module. The Emotion Module analyses a picture of the user's face and uses the CNN algorithm to detect their mood with an accuracy of more than 95%. The Music Classification Module gets an outstanding result by utilizing aural criteria while classifying music into 4 different mood groups. The recommendation module suggests music to users by comparing their feelings to the mood type of the song. taking the user's preferences into account.
Keywords: CNN .
DOI: https://doi.org/10.5281/zenodo.8042843
PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT23JUN354.pdf
REFERENCES