Expressive Performance with Bayesian Networks and Linear Basis Models.

Sebastian Flossmann; Maarten Grachten; Gerhard Widmer

Expressive Performance with Bayesian Networks and Linear Basis Models.

Sebastian Flossmann, Maarten Grachten, Gerhard Widmer

Institute of Computational Perception

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

Abstract

Expressive music performance is a complex task that appears to require heterogeneous information, varying from one expressive dimension to another. For example, loudness is guided to a considerable extent by annotations in the score, whereas overall performance tempo is more related to phrasing [1]. Timing and articulation on the other hand may depend more on local score information. The system we present takes a modular approach that treats dynamics, articulation, timing and global tempo in different ways.

Original language	English
Title of host publication	Rencon Workshop 2011: Musical Performance Rendering competition for Computer Systems.
Number of pages	2
Publication status	Published - 2011

Fields of science

102 Computer Sciences
102001 Artificial intelligence
102003 Image processing

JKU Focus areas

Computation in Informatics and Mathematics
Engineering and Natural Sciences (in general)

Cite this

@inproceedings{5034679d7eb24daab6707e8d9d829b98,

title = "Expressive Performance with Bayesian Networks and Linear Basis Models.",

abstract = "Expressive music performance is a complex task that appears to require heterogeneous information, varying from one expressive dimension to another. For example, loudness is guided to a considerable extent by annotations in the score, whereas overall performance tempo is more related to phrasing [1]. Timing and articulation on the other hand may depend more on local score information. The system we present takes a modular approach that treats dynamics, articulation, timing and global tempo in different ways.",

author = "Sebastian Flossmann and Maarten Grachten and Gerhard Widmer",

year = "2011",

language = "English",

booktitle = "Rencon Workshop 2011: Musical Performance Rendering competition for Computer Systems.",

}

TY - GEN

T1 - Expressive Performance with Bayesian Networks and Linear Basis Models.

AU - Flossmann, Sebastian

AU - Grachten, Maarten

AU - Widmer, Gerhard

PY - 2011

Y1 - 2011

N2 - Expressive music performance is a complex task that appears to require heterogeneous information, varying from one expressive dimension to another. For example, loudness is guided to a considerable extent by annotations in the score, whereas overall performance tempo is more related to phrasing [1]. Timing and articulation on the other hand may depend more on local score information. The system we present takes a modular approach that treats dynamics, articulation, timing and global tempo in different ways.

AB - Expressive music performance is a complex task that appears to require heterogeneous information, varying from one expressive dimension to another. For example, loudness is guided to a considerable extent by annotations in the score, whereas overall performance tempo is more related to phrasing [1]. Timing and articulation on the other hand may depend more on local score information. The system we present takes a modular approach that treats dynamics, articulation, timing and global tempo in different ways.

M3 - Conference proceedings

BT - Rencon Workshop 2011: Musical Performance Rendering competition for Computer Systems.

ER -