Multi-Modal Song Mood Detection with Deep Learning.

Konstantinos Pyrovolakis,Paraskevi Tzouveli,Giorgos Stamou

doi:10.3390/s22031065

Konstantinos Pyrovolakis, Paraskevi Tzouveli + Show 1 more

Open Access

https://doi.org/10.3390/s22031065

Copy DOI

Abstract

The production and consumption of music in the contemporary era results in big data generation and creates new needs for automated and more effective management of these data. Automated music mood detection constitutes an active task in the field of MIR (Music Information Retrieval). The first approach to correlating music and mood was made in 1990 by Gordon Burner who researched the way that musical emotion affects marketing. In 2016, Lidy and Schiner trained a CNN for the task of genre and mood classification based on audio. In 2018, Delbouys et al. developed a multi-modal Deep Learning system combining CNN and LSTM architectures and concluded that multi-modal approaches overcome single channel models. This work will examine and compare single channel and multi-modal approaches for the task of music mood detection applying Deep Learning architectures. Our first approach tries to utilize the audio signal and the lyrics of a musical track separately, while the second approach applies a uniform multi-modal analysis to classify the given data into mood classes. The available data we will use to train and evaluate our models comes from the MoodyLyrics dataset, which includes 2000 song titles with labels from four mood classes, {happy, angry, sad, relaxed}. The result of this work leads to a uniform prediction of the mood that represents a music track and has usage in many applications.

Highlights

The terms music and emotion are two concepts that are strongly connected, from the very first moment that man invented music
Automated music mood detection constitutes an active task in the field of Music
We look at the histogram of the words within the lyrics document, i.e., considering each word count as a feature

Summary

Introduction

The terms music and emotion are two concepts that are strongly connected, from the very first moment that man invented music. Special scientific interest presents the way that music causes emotional arousal to listener. A track of music will cause the same emotions in a set of listeners, there are a lot of factors responsible for the way a track will be perceived and will differ from listener to listener. Listeners’ backgrounds and tastes in music are two of the most important factors that will determine the emotions felt listening to a music track, but are not the only ones. According to Hunter [1], the emotional state and environment of the listener when the musical stimulus is received play an important role.

Objectives

Methods

Results

Conclusion