AI based Music Recommendation System Using Deep Learning

The customized recommendation framework for music should accurately represent private tastes. To obtain tailored feedback for the needs of various viewers, it takes adjustments. To find the better  deep  learning  model  for  the  recommendation  may  p

Project Title

Project Area of Specialization

Artificial Intelligence

Project Summary

The customized recommendation framework for music should accurately represent private tastes. To obtain tailored feedback for the needs of various viewers, it takes adjustments. To find the

better deep learning model for the recommendation may pave a way for a better recommender.

Compared to the previous era, with commercial music streaming sites that can be downloaded from mobile devices, digital music availability is currently plentiful. It takes a very long time to figure out all this digital music and induces data exhaustion. It may be helpful to create a music recommendation system that can automatically scan the music libraries and suggest appropriate songs to users. The music provider will anticipate and then give their customers the appropriate songs based on the

characteristics of the music previously heard by using the music recommendation system. Our Project would like to build a framework for music recommendations that can provide recommendations based on the similarity of audio signal features. This project uses the Convolutional Neural Network

(CNN) and the Recurrent Neural Network (RNN). Customized recommendation system for music should effectively represent private preferences. To attain tailored recommendations for the demands of different listeners, it needs changes and therefore, attempting to find a better deep learning model for the recommendation will pave a way for a better recommender.

Project Objectives

To find the better deep learning model for the recommendation of music.
To create a music recommendation system that can automatically scan the music libraries and suggest appropriate songs to users.
To provide a system that can provide recommendations based on the similarity of audio signal features.

Project Implementation Method

CNN was inspired by the visual cortex of the brain and prominently used for object or face detection and classification.

CNN have three-dimensional layers height, width and depth and all neurons are not connected to the previous layer

rather a layer is only connected to a small portion of neurons in the previous layer. LSTM is also a deep learning

algorithm to selectively remember patterns for long duration of time and to overcame long term dependencies problem

of RNN. LSTM just does some changes to information by implementing multiplication and addition.In this work, a

deep learning prototype is recommended for the automatic classification of different of audio signals. The proposed

CNN and LSTM model has an end-to-end architecture with MFCC feature extraction methods.

As we all know that CNN understands the data accurately using an image. So, at first, we need to convert our audio data

into image. To visualize the data, plot the amplitude versus the time graph but it becomes harder to study the response

so the frequency graph utilized for that purpose using fast Fourier transform and we notice that data becomes more

reluctant at low frequency so further we would down-sample the data (say to maybe 16Khz).