Use of Variational Inference in Music Emotion Recognition

TL;DR

This paper introduces a Bayesian statistical approach using variational inference for Music Emotion Recognition, aiming to develop adaptable models that enhance interpretation and regularization in emotion-based music recommendation systems.

Contribution

It applies modern Bayesian techniques to Music Emotion Recognition, creating a flexible multivariate model that improves statistical analysis and regularization in the field.

Findings

Developed an efficient Bayesian algorithm for emotion recognition in music.

Demonstrated the model's adaptability to various databases.

Enhanced interpretability of emotion-related data in music.

Abstract

This work was developed aiming to employ Statistical techniques to the field of Music Emotion Recognition, a well-recognized area within the Signal Processing world, but hardly explored from the statistical point of view. Here, we opened several possibilities within the field, applying modern Bayesian Statistics techniques and developing efficient algorithms, focusing on the applicability of the results obtained. Although the motivation for this project was the development of a emotion-based music recommendation system, its main contribution is a highly adaptable multivariate model that can be useful interpreting any database where there is an interest in applying regularization in an efficient manner. Broadly speaking, we will explore what role a sound theoretical statistical analysis can play in the modeling of an algorithm that is able to understand a well-known database and what can be gained with this kind of approach.