Music Recommender System Based on Genre using Convolutional Recurrent Neural Networks

With commercial music streaming service which can be accessed from mobile devices, the availability of digital music currently is abundant compared to previous era. Sorting out all this digital music is a very time-consuming and causes information fatigue. Therefore, it is very useful to develop a music recommender system that can search in the music libraries automatically and suggest suitable songs to users. By using music recommender system, the music provider can predict and then offer the appropriate songs to their users based on the characteristics of the music that has been heard previously. Our research would like to develop a music recommender system that can give recommendations based on similarity of features on audio signal. This study uses convolutional recurrent neural network (CRNN) for feature extraction and similarity distance to look similarity between features. The results of this study indicate that users prefer recommendations that consider music genres compared to recommendations based solely on similarity. (C) 2019 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/) Peer-review under responsibility of the scientific committee of the 4th International Conference on Computer Science and Computational Intelligence 2019.