Machine Learning-Driven Music Recognition: From Feature Extraction to Performance Optimization

Presenter(s)

Redeate Kidanue

Abstract or Description

Music is a tool that has been integrated into society for thousands of years, it has influenced social aspects of life and has also aided in communication. Today we have various uses for music that go past our traditional entertainment uses and self-expression. Commonly, we see music being incorporated into visual art forms, and also being used in the medical field, specifically music therapy. With this broad spectrum of usage, it is important that music stays organized and easily accessible. This project intends to review literature looking at the methods, results, and limitations of music recognition using machine learning. Various techniques like K-Nearest Neighbor, Deep Neural Networks, and Convolutional Neural Networks have been identified in the use of organizing music and audio files by genre and utility. This literature review will also explore methods of data acquisition and music information retrieval. This paper focuses on presenting various learning models in the field of music recognition and illustrating their results

Mentor

Rushit Dave