• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
10.11606/D.45.2018.tde-22122017-164922
Document
Author
Full name
Roberto Piassi Passos Bodo
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Paulo, 2015
Supervisor
Committee
Queiroz, Marcelo Gomes de (President)
Iazzetta, Fernando Henrique de Oliveira
Kon, Fabio
Title in Portuguese
Técnicas determinísticas para acompanhamento musical automatizado
Keywords in Portuguese
Acompanhamento musical
Computação musical
Rastreamento de partitura
Abstract in Portuguese
Sistemas de acompanhamento musical automatizado são de grande utilidade como ferramentas didáticas. Com eles, um aluno de música consegue ensaiar uma peça musical sendo acompanhado pelo computador, com a liberdade de tocar na velocidade em que desejar e, além disso, de cometer erros acidentais ou desvios intencionais em relação ao esperado (definido em partitura). Um sistema de acompanhamento musical deve ter as habilidades de analisar a execução ao vivo de um músico (pré-processador da entrada), comparar os eventos recebidos com os de uma partitura pré-carregada (rastreador), gerar o acompanhamento conforme o andamento inferido (acompanhador) e sintetizar os sons relativos a esse acompanhamento (sintetizador). O trabalho apresentado neste texto consistiu em estudar diversas técnicas relativas ao problema de acompanhamento musical, implementar alguns algoritmos baseados na literatura abordada, validar a qualidade obtida com tais algoritmos e disponibilizar um sistema de código aberto modular com mais de uma alternativa de algoritmo para cada módulo. Além disso, foi desenvolvido um elemento adicional para o sistema - o MetaRastreador - que combina todas as técnicas de rastreamento implementadas, executando-as em paralelo e obtendo uma maior confiabilidade nas informações extraídas da entrada, considerando diversas opiniões diferentes sobre a posição do músico na partitura.
Title in English
Deterministic techniques for automated musical accompaniment
Keywords in English
Computer music
Musical accompaniment
Score following
Abstract in English
Automated musical accompaniment systems are very useful as didactic tools. With them, a music student can rehearse a musical piece being accompanied by the computer, with the freedom to play at the desired speed and, moreover, to perform accidental errors or intentional deviations from the expected (defined by a musical score). A musical accompaniment system should have the skills to analyze the live performance of a musician (input preprocessor), compare the events received with those of a preloaded score (matcher), generate the accompaniment according to the inferred tempo (accompaniment), and synthesize the sounds related to this accompaniment (synthesizer). The work presented in this text consisted of studying several techniques related to the musical accompaniment problem, implementing some algorithms based on the literature, validating the quality obtained with such algorithms, and providing a modular open source system with more than one alternative algorithm for each module. Furthermore, an additional element was developed for the system - the MetaMatcher - that combines all the tracking techniques implemented by running them in parallel and obtaining a greater reliability in the information extracted from the input, considering several different opinions about the position of the musician in the musical score.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2018-02-19
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2019. All rights reserved.