Analysis of an input dataset to perform a tonal analysis system

• Autores: Vilca Rojas, Víctor Manuel, Salcedo Chávez, Aldair Bryan, Castillo Rojas, Jairo Miguel, Byrne Macias, Valery
• Formato: artículo
• Fecha de Publicación: 2023
• Institución: Universidad La Salle
• Repositorio: Revistas - Universidad La Salle
• Lenguaje: español
• OAI Identifier: oai:ojs.revistas.ulasalle.edu.pe:article/85
• Enlace del recurso: https://revistas.ulasalle.edu.pe/innosoft/article/view/85; https://doi.org/10.48168/innosoft.s11.a85; https://purl.org/42411/s11/a85; https://n2t.net/ark:/42411/s11/a85
• Nivel de acceso: acceso abierto
• Materia: Artificial intelligence; decision tree; music analysis; pitch detection; music; Inteligencia artificial; árbol de decisión; análisis musical; detección de tonos; música

Musical analysis is a process that has been carried out for years where different experts have sought to study various musical pieces. This process begins with the learning of tone, note and chord detection, where students have to train their ears to be able to carry it out. In this context, in the following work a decision tree has been made based on a dataset of Bach choirs in order to predict chords from tones. The dataset was divided into 80% to create the tree and 20% for testing, then the data transformation was performed to perform an analysis of the data, with this a decision tree was finally created with a depth of 15 and an accuracy of 75.52%, the tests were finally carried out and we found good results for the accuracy of the tree.