Publicação

Real-time MIDI device data analysis and context aware music generation

Ver documento

Detalhes bibliográficos
Resumo:Computer music generation is an active research field encompassing a wide range of approaches. As we involve more and more technology in our creative endeavors, it becomes vital that we provide our systems with the capability to understand and represent art concepts internally, as well as understand and predict artistic intent and emotion. In respect to music, being able to work with this information opens up fantastic possibilities for artistmachine synergetic collaborations as well as machine creativity endeavors. In this spirit, this dissertation explores a system capable of analyzing in real-time a performance piece played on a MIDI (Musical Instrument Digital Interface) capable instrument and produce a musically coherent piece of accompaniment music. This system comprises of two major subsystems: one responsible for analyzing and extracting features from the live performance and one that takes these features and generates MIDI tracks to be played in conjunction with the live audio, in a way that blends in with the performance.
Autores principais:Ribeiro, Miguel Angelo Ferreira Dias
Assunto:Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática
Ano:2017
País:Portugal
Tipo de documento:dissertação de mestrado
Tipo de acesso:acesso aberto
Instituição associada:Universidade do Minho
Idioma:inglês
Origem:RepositóriUM - Universidade do Minho
Descrição
Resumo:Computer music generation is an active research field encompassing a wide range of approaches. As we involve more and more technology in our creative endeavors, it becomes vital that we provide our systems with the capability to understand and represent art concepts internally, as well as understand and predict artistic intent and emotion. In respect to music, being able to work with this information opens up fantastic possibilities for artistmachine synergetic collaborations as well as machine creativity endeavors. In this spirit, this dissertation explores a system capable of analyzing in real-time a performance piece played on a MIDI (Musical Instrument Digital Interface) capable instrument and produce a musically coherent piece of accompaniment music. This system comprises of two major subsystems: one responsible for analyzing and extracting features from the live performance and one that takes these features and generates MIDI tracks to be played in conjunction with the live audio, in a way that blends in with the performance.