Department of Computer Science - Institute of Mathematics and Statistics - University of São Paulo - Brazil
Languages
Past talks
Speaker: MsC. Lorenzo Porcaro
Date and time: Tuesday, March 29, 2022 - 08:00
Place: https://meet.jit.si/CompmusSeminário (apenas em caso de dificuldades técnicas, usaremos como endereço alternativo o https://meet.google.com/vhb-wfxh-pwt)
Abstract: Music Recommender Systems (Music RS) are nowadays pivotal in shaping the listening experience of people all around the world. Thanks also to their widespread use in music streaming services, it has been possible to enhance several characteristics of such systems in terms of performance, design, and user experience. Nonetheless, imagining Music RS only from an application-driven perspective may generate an incomplete view of how this technology is affecting people’s habitus, from the decision- making processes to the formation of musical taste and opinions. In this talk, I will address the concept of diversity in music recommendation, and taking a value-driven approach, I will discuss diversity-related methodologies proposed in the Music RS literature. Maintaining an interdisciplinary perspective, I will discuss some challenges that MIR practitioners may face when researching Music RS, going beyond the search for better performance and instead questioning the theoretical foundations on which to base future research.
Porcaro, L., Castillo, C. and Gómez, E., 2021. Diversity by Design in Music Recommender Systems. Transactions of the International Society for Music Information Retrieval, 4(1), pp.114–126. DOI: http://doi.org/10.5334/tismir.106
(presentation in Portuguese)
Date and time: Tuesday, March 29, 2022 - 08:00
Place: https://meet.jit.si/CompmusSeminário (apenas em caso de dificuldades técnicas, usaremos como endereço alternativo o https://meet.google.com/vhb-wfxh-pwt)
Abstract: Music Recommender Systems (Music RS) are nowadays pivotal in shaping the listening experience of people all around the world. Thanks also to their widespread use in music streaming services, it has been possible to enhance several characteristics of such systems in terms of performance, design, and user experience. Nonetheless, imagining Music RS only from an application-driven perspective may generate an incomplete view of how this technology is affecting people’s habitus, from the decision- making processes to the formation of musical taste and opinions. In this talk, I will address the concept of diversity in music recommendation, and taking a value-driven approach, I will discuss diversity-related methodologies proposed in the Music RS literature. Maintaining an interdisciplinary perspective, I will discuss some challenges that MIR practitioners may face when researching Music RS, going beyond the search for better performance and instead questioning the theoretical foundations on which to base future research.
Porcaro, L., Castillo, C. and Gómez, E., 2021. Diversity by Design in Music Recommender Systems. Transactions of the International Society for Music Information Retrieval, 4(1), pp.114–126. DOI: http://doi.org/10.5334/tismir.106
(presentation in Portuguese)
Speaker: Profa. Dra. Marcela Rodrigues Machado (UnB)
Date and time: Tuesday, November 30, 2021 - 13:00
Place: https://meet.jit.si/CompmusSeminário (in case of technical difficulties: https://meet.google.com/vhb-wfxh-pwt)
Abstract: (Abstract in Portuguese)
(presentation in Portuguese)
Date and time: Tuesday, November 30, 2021 - 13:00
Place: https://meet.jit.si/CompmusSeminário (in case of technical difficulties: https://meet.google.com/vhb-wfxh-pwt)
Abstract: (Abstract in Portuguese)
A análise de um sistema dinâmico e sua modelagem depende de vários fatores que podem implicar na sua performance. Estes modelos podem ser definidos como a idealização matemática dos processos físicos que regem sua evolução. Isso requer definições de variáveis básicas como a descrição da geometria do sistema, carregamento, propriedades do material, eventos externos, variáveis de resposta em deslocamento, deformação, tensões, e as relações entre essas várias quantidades. Neste cenário, as perguntas são: Como a incerteza do sistema impacta a sua resposta dinâmica? Qual é o significado físico? Como podemos modelar a incerteza em sistemas dinâmicos? Nós ‘sabemos’ a fonte das incertezas? Como podemos quantificar a incerteza de forma eficiente na resposta dinâmica? Nas últimas décadas, várias pesquisas foram desenvolvidas a fim de responder a essas perguntas. Nesta palestra, algumas dessas indagações são abordadas e exploradas.
(presentation in Portuguese)
Speaker: Vitor Kisil (NuSom/USP e FIAP)
Date and time: Tuesday, October 19, 2021 - 13:00
Place: https://meet.jit.si/CompmusSeminário (apenas em caso de dificuldades técnicas, usaremos como endereço alternativo o https://meet.google.com/vhb-wfxh-pwt)
Abstract: (abstract in Portuguese)
(presentation in Portuguese)
Date and time: Tuesday, October 19, 2021 - 13:00
Place: https://meet.jit.si/CompmusSeminário (apenas em caso de dificuldades técnicas, usaremos como endereço alternativo o https://meet.google.com/vhb-wfxh-pwt)
Abstract: (abstract in Portuguese)
Através de uma narrativa pessoal e de exemplos artísticos autorais busco introduzir algumas reflexões sobre questões amplas e complexas envolvendo a criação contemporânea, como: a técnica e a tecnologia na elaboração de produções artísticas individuais e coletivas; a abordagem experimental e laboratorial como prática e processo de criação; a interação entre distintas áreas de conhecimento na elaboração de projetos artísticos; e a busca por desajustes e rupturas - em nível pessoal e/ou comunitário - como geradores de questões técnicas, poéticas e estéticas que estimulem o desenvolvimento artístico.
Vitor Kisil:
Compositor, intérprete, pesquisador e professor com atuação em diversas formas de manifestação musical, como desenvolvimento e apresentação de performances interativas, criação de trilhas para produções audiovisuais e apresentações musicais como intérprete e criador. É mestre e doutor em música pela USP. Foi contemplado com prêmios de melhor trilha sonora para curtas-metragens em festivais no país e no exterior. Atua regularmente em grupos de arte interativa como compositor e responsável pela elaboração e desenvolvimento das ferramentas de processamento e manipulação de áudio em tempo real. Em 2020 lançou o disco musical “Convergência Procedimental: Registro, Performance e Escrita em Processamentos Musicais”. É membro do NuSom (USP) e um dos fundadores do Grupo de Práticas Interativas (GPI - NuSom). Atualmente é professor do curso de Jogos Digitais da FIAP.
(presentation in Portuguese)
Speaker: Dr. Guilherme Paiva, Dr. Rodolfo Thomazelli e Guilherme Fontebasso
Date and time: Tuesday, October 5, 2021 - 13:00
Place: https://meet.jit.si/CompmusSeminário (just in case of technical difficulties, we will use as an alternative address https://meet.google.com/vhb-wfxh-pwt)
Abstract:
(presentation in Portuguese)
Date and time: Tuesday, October 5, 2021 - 13:00
Place: https://meet.jit.si/CompmusSeminário (just in case of technical difficulties, we will use as an alternative address https://meet.google.com/vhb-wfxh-pwt)
Abstract:
The musical instruments manufacturing involves several design demands related both to the instrument's structural capacity, as well as to the desired sound and aesthetic attributes. Although there have been, for at least two decades, technologies available to assist these projects, much of what has been done is the empirical reproduction of consolidated models: a process that makes innovation difficult because it is often based on trial and error methods. Computational tools, therefore, are useful because they allow a certain level of prediction of the instrument's structural behavior and the sound that will be produced, enabling the reduction of both the time and costs involved in the instrument's design and construction.
In this context, the startup Turbonius R&D has been dedicated to developing a computational platform (Urutau Platform) implemented in the cloud to support designers and builders of musical instruments on small and large scales. In this presentation, the architecture of the computational environment under development will be briefly described, as well as the methods used for modeling and synthesizing stringed musical instruments.
In order to verify the applied methodology, comparisons between synthesized sounds and the corresponding sounds obtained experimentally are presented. Finally, preliminary examples of the application of the computational platform in the design of a stringed musical instrument are shown.
(presentation in Portuguese)
Speaker: Dr. Marcelo Caetano
Date and time: Tuesday, September 21, 2021 - 13:00
Place: https://meet.jit.si/CompmusSeminário (apenas em caso de dificuldades técnicas, usaremos como endereço alternativo o https://meet.google.com/vhb-wfxh-pwt)
Abstract:
(video presentation in portuguese)
Date and time: Tuesday, September 21, 2021 - 13:00
Place: https://meet.jit.si/CompmusSeminário (apenas em caso de dificuldades técnicas, usaremos como endereço alternativo o https://meet.google.com/vhb-wfxh-pwt)
Abstract:
The MORPH project proposes to use sound morphing to investigate timbre in traditional musical instruments. Timbre is a complex multi-dimentional perceptual phenomenon considered to be one of the last frontiers of auditory science. Sound morphing is a transformation that gradually blurs the categorical distinction between sounds by blending their sensory attributes. We will use sound morphing to create continuous timbre spaces by filling the gaps between traditional musical instruments, therefore breaking the categorical perception of musical instrument timbre by the auditory illusion of hybrid musical instruments. Then, we will integrate a touch user interface to enable the creative exploration of the timbral gap between traditional musical instrument sounds with morphing. Thus, sound morphing has the potential to advance our understanding of musical timbre and to deliver innovative virtual hybrid musical instruments that push the boundaries of musical expression by moving beyond the physical limitations of acoustic musical instruments and the traditional digital musical instruments that rely on them.
Acknowledgement: This project has received funding from the European Union’s Horizon 2020 research and Innovation programme under the Marie Sklodowska-Curie grant agreement No 831852 (MORPH).
(video presentation in portuguese)
Pages
