Identifying attack articulations in classical guitar

Authors:
Tan Hakan Özaslan;Enric Guaus;Eric Palacios;Josep Lluis Arcos
Affiliations:
Artificial Intelligence Research Institute, Spanish National Research Council, Bellaterra, Spain;Artificial Intelligence Research Institute, Spanish National Research Council, Bellaterra, Spain;Artificial Intelligence Research Institute, Spanish National Research Council, Bellaterra, Spain;Artificial Intelligence Research Institute, Spanish National Research Council, Bellaterra, Spain
Venue:
CMMR'10 Proceedings of the 7th international conference on Exploring music contents
Year:
2010

Citing 6
Cited 1

Computer Music: Synthesis, Composition, and Performance

Computer Music: Synthesis, Composition, and Performance
AI and music from composition to expressive performance

AI Magazine
Visual methods for the retrieval of guitarist fingering

NIME '06 Proceedings of the 2006 conference on New interfaces for musical expression
A case based approach to expressivity-aware tempo transformation

Machine Learning
Experiencing SAX: a novel symbolic representation of time series

Data Mining and Knowledge Discovery
A Constraint-based Approach for Annotating Music Scores with Gestural Information

Constraints

Analyzing musical expressivity with a soft computing approach

Fuzzy Sets and Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

The study of musical expressivity is an active field in sound and music computing. The research interest comes from different motivations: to understand or model music expressivity; to identify the expressive resources that characterize an instrument, musical genre, or performer; or to build synthesis systems able to play expressively. Our research is focused on the study of classical guitar and deals with modeling the use of the expressive resources in the guitar. In this paper, we present a system that combines several state of the art analysis algorithms to identify guitar left hand articulations such as legatos and glissandos. After describing the components of our system, we report some experiments with recordings containing single articulations and short melodies performed by a professional guitarist.