Song Emotion Recognition: a Performance Comparison Between Audio Features and Artificial Neural Networks

When songs are composed or performed, there is often an intent by the singer/songwriter of expressing feelings or emotions through it. For humans, matching the emotiveness in a musical composition or performance with the subjective perceptiveness of an audience can be quite challenging. Fortunately,...

Descripción completa

Detalles Bibliográficos
Autores: Benevenuto Valadares, Pedro, Rosero Jácome, Karen Gissell, dos Santos, Arthur Nicholas, Sanches Masiero, Bruno
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2022
País:Brasil
Institución:Sociedade Brasileira de Computação (SBC)
Repositorio:Revista Eletrônica de Iniciação Científica
Idioma:inglés
OAI Identifier:oai:journals-sol.sbc.org.br:article/2766
Acceso en línea:https://journals-sol.sbc.org.br/index.php/reic/article/view/2766
Access Level:acceso abierto
Palabra clave:Deep learning
Neural networks
Emotion recognition
Digital signal processing
Music Information Retrieval
Descripción
Sumario:When songs are composed or performed, there is often an intent by the singer/songwriter of expressing feelings or emotions through it. For humans, matching the emotiveness in a musical composition or performance with the subjective perceptiveness of an audience can be quite challenging. Fortunately, the machine learning approach for this problem is simpler. Usually, it takes a data-set, from which audio features are extracted to present this information to a data-driven model, that will, in turn, train predicting the highest probability of an input song matching a target emotion. In this paper, we studied the most common features and models used in recent publications to tackle this problem, revealing which ones are best suited for songs a cappella.