User Curated Shaping of Expressive Performances

TL;DR

This paper introduces an interactive interface that allows users to explore how score features influence expressive musical performances, based on a neural network model that links score elements to expressive parameters.

Contribution

It presents a novel user interface for manipulating and understanding the relationship between score features and expressive performance using data-driven models.

Findings

Users can customize expressive parameters by weighting score features.

The interface provides insights into how score elements shape performance.

Neural network models effectively capture the relationship between score and expression.

Abstract

Musicians produce individualized, expressive performances by manipulating parameters such as dynamics, tempo and articulation. This manipulation of expressive parameters is informed by elements of score information such as pitch, meter, and tempo and dynamics markings (among others). In this paper we present an interactive interface that gives users the opportunity to explore the relationship between structural elements of a score and expressive parameters. This interface draws on the basis function models, a data-driven framework for expressive performance. In this framework, expressive parameters are modeled as a function of score features, i.e., numerical encodings of specific aspects of a musical score, using neural networks. With the proposed interface, users are able to weight the contribution of individual score features and understand how an expressive performance is constructed.