Global ETD Search

1	Métodos de segmentação musical baseados em descritores sonoros / Musical segmentation methods based on sound descriptors Pires, André Salim 20 June 2011 (has links) Esta dissertação apresenta um estudo comparativo de diferentes métodos computacionais de segmentação estrutural musical, onde o principal objetivo é delimitar fronteiras de seções musicais em um sinal de áudio, e rotulá-las, i.e. agrupar as seções encontradas que correspondem a uma mesma parte musical. São apresentadas novas propostas para segmentação estrutural nãosupervisionada, incluindo métodos para processamento em tempo real, alcançando resultados com taxas de erro inferiores a 12%. O método utilizado compreende um estudo dos descritores sonoros e meios de modelá-los temporalmente, uma exposição das técnicas computacionais de segmentação estrutural e novos métodos de avaliação dos resultados que penalizam tanto a incorreta detecção das fronteiras quanto o número incorreto de rótulos encontrados. O desempenho de cada técnica computacional é calculado utilizando diferentes conjuntos de descritores sonoros e os resultados são apresentados e analisados tanto quantitativa quanto qualitativamente. / A comparative study of different music structural segmentation methods is presented, where the goal is to delimit the borders of musical sections and label them, i.e. group the sections that correspond to the same musical part. Novel proposals for unsupervised segmentation are presented, including methods for real-time segmentation, achieving expressive results, with error ratio less then 12%. Our method consists of a study of sound descriptors, an exposition of the computational techniques for structural segmentation and the description of the evaluation methods utilized, which penalize both incorrect boundary detection and incorrect number of labels. The performance of each technique is calculated using different sound descriptor sets and the results are presented and analysed both from quantitative and qualitative points-of-view. music information retrieval music structural segmentation real-time music segmentation real-time sound processing recuperação de informação musical segmentação estrutural musical segmentação musical em tempo real
2	Métodos de segmentação musical baseados em descritores sonoros / Musical segmentation methods based on sound descriptors André Salim Pires 20 June 2011 (has links) Esta dissertação apresenta um estudo comparativo de diferentes métodos computacionais de segmentação estrutural musical, onde o principal objetivo é delimitar fronteiras de seções musicais em um sinal de áudio, e rotulá-las, i.e. agrupar as seções encontradas que correspondem a uma mesma parte musical. São apresentadas novas propostas para segmentação estrutural nãosupervisionada, incluindo métodos para processamento em tempo real, alcançando resultados com taxas de erro inferiores a 12%. O método utilizado compreende um estudo dos descritores sonoros e meios de modelá-los temporalmente, uma exposição das técnicas computacionais de segmentação estrutural e novos métodos de avaliação dos resultados que penalizam tanto a incorreta detecção das fronteiras quanto o número incorreto de rótulos encontrados. O desempenho de cada técnica computacional é calculado utilizando diferentes conjuntos de descritores sonoros e os resultados são apresentados e analisados tanto quantitativa quanto qualitativamente. / A comparative study of different music structural segmentation methods is presented, where the goal is to delimit the borders of musical sections and label them, i.e. group the sections that correspond to the same musical part. Novel proposals for unsupervised segmentation are presented, including methods for real-time segmentation, achieving expressive results, with error ratio less then 12%. Our method consists of a study of sound descriptors, an exposition of the computational techniques for structural segmentation and the description of the evaluation methods utilized, which penalize both incorrect boundary detection and incorrect number of labels. The performance of each technique is calculated using different sound descriptor sets and the results are presented and analysed both from quantitative and qualitative points-of-view. recuperação de informação musical segmentação estrutural musical segmentação musical em tempo real music information retrieval music structural segmentation real-time music segmentation real-time sound processing
3	Mot händelsernas horisont : Att komponera improviserad musik med ljuddesign som metod Jonsäll, Hans Lennart January 2021 (has links) This Bachelor Thesis in composition explores an alternative compositional process for creating improvised music through the approach of sound design. The questions addressed in the thesis are concerned with how the soundscape can be controlled by the composer while still maintaining the expressivity of an improvised performance. Thus, the composer’s role as both sound designer, producer and performer is investigated using live electronics and score design. The theoretical framework for the thesis is to be found in the intersection between Anglo-American experimental music, electronic music, sound design and electroacoustic improvisation. Key influences include indeterminacy as expressed in the music of John Cage, Deep Listening practices pioneered by Pauline Oliveros as well as the aesthetical paradigms of electronic and electroacoustic music. The artistic methods revolved around the following steps: studio workshops with musicians (Fredrik Ekenvi and José Louis Relova Gallego) exploring timbres, playing techniques and music technology in real-time followed by associative discussions about the soundscapes created; composing audio and graphical drafts influenced by the workshops; designing diagrams for the electronics and compiling these to a design document; workshopping and performing the final piece (Towards the Event Horizon). Towards the Event Horizon (for bass clarinet, electric guitar and live electronics) is the final result of the work, comprising a score with accompanying design document as well as a recording of the original performance at Studio Acusticum in Piteå 20th of March 2021. The artefacts and associated documentation are presented in their entirety on the dedicated Research Catalogue exposition. Conclusions include how composition and sound design are tied together and cannot be considered as isolated processes, especially in the context of live electronics; the interrelationship between the improviser, the acoustic soundscape and the artistic associations that inform the improvisation; the importance of form as the defining element of a composition and lastly; how a score for improvised music can be devised in the shape of a blueprint of form and texture, setting certain technical, sonic and gestural conditions while leaving the performer to play freely within this frame. / <p>Konstnärliga artefakter presenteras via Research Catalogue: https://www.researchcatalogue.net/view/1250652/1250651</p> Composition Experimental music Electronic music Electroacoustic music Electroacoustic improvisation Graphical scores Live electronics Sound design Sound art Sound engineering Music production Digital sound processing Real-time sound processing John Cage Pauline Oliveros Deep Listening Indeterminacy Komposition Experimentell musik Elektronisk musik Elektroakustisk musik Elektroakustisk improvisation Grafiska partitur Live-elektronik Ljuddesign Ljudkonst Ljudteknik Musikproduktion Digitalt ljud realtidsprocessning John Cage Pauline Oliveros Deep Listening Indeterminacy Music Musik

1

Page generated in 0.1274 seconds