BMNet-5: A Novel Approach of Neural Network to Classify the Genre of Bengali Music Based on Audio Features

Aim:

          The proposed BMNet-5 is based on a neural network designed to predict music genre from audio inputs

Abstract:

           There are billions of peoples listening millions of music in this world. Now a day’s music plays a vital role in people’s life. It closely related to their emotions. So we are here to provide a solutions for this recommendation based on the user mood. Music Genre Classification (MGC) can be used in a lot of ways to organize and manage music recommendation systems, advertising, and streaming services. But there have been a lot of works on classifying English music using different statistical and machine learning methods.

 Problem Definition:

              The problem is to create a solutions for recommending music based on mood.

Existing System: 

             We there are lots of existing system available in this concept but the accuracy is low. In existing system they have used CNN which is very good for audio and image data’s but still we can able to achieve the good one.

Proposed:

             There we have used XGBOOST algorithm in proposed system. When its compared with base paper our accuracy is improved better than previous one. We have also tried for realtime implementation.