Aprendizado de máquina aplicado à pedagogia da improvisação musical

• Ano de defesa: 2023
• Autor(a) principal: Martins, Tiago Leandro
• Orientador(a): Basbaum, Sérgio Roclaw
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Pontifícia Universidade Católica de São Paulo
• Programa de Pós-Graduação: Programa de Estudos Pós-Graduados em Tecnologias da Inteligência e Design Digital
• Departamento: Faculdade de Ciências Exatas e Tecnologia
• País: Brasil
• Palavras-chave em Português: Aprendizado de máquina; Pedagogia; Improvisação musical; Engenharia de características
• Palavras-chave em Inglês: Machine learning; Pedagogy; Musical improvisation; Features engineering
• Área do conhecimento CNPq: CNPQ::ENGENHARIAS
• Link de acesso: https://repositorio.pucsp.br/jspui/handle/handle/40864

Musical improvisation has been performed by programable machines for a long time, which reinforces the question about the role technology plays in culture and how it could better assist humans in complex topics and open domains. It’s possible to verify a number of artificial intelligence-based applications, with technology and performance on the spot while literature relating AI aspects to musical improvisation pedagogy in popular music is scarse. This research explores how machine learning aspects, as features engineering, could better assist the human cognition in such complex topic as the musical improvisation, using machine learning techniques to explicit idiomatic improvisational rules found in the literature from a digital database containing transcribed recordings. Even though relationships have been found, there are a number of parameters to be considered in order to encompass all the complexity behind this subject.