On the role of artificial intelligence in music research

Abstract

This paper gives a partial overview of what is currently going on in the emerging field known as Artificial Intelligence and Music (AIM). In particular, it focuses on Artificial Intelligence (AI) research areas which, according to a personal view, can significantly influence current music research. The paper highlights how AIM is not a field in which AI technology is merely applied to music. Both music and the AI field can benefit from studies in this discipline: music is a complex experimental domain which can be particularly useful in the formulation and verification of theories about intelligence. This hypothesis is confirmed by the recent works in this field, and particularly by the papers included in this issue of Interface. This paper attempts to set them against an AI global view. The author focuses on the role of some knowledge representation paradigms, such as logic-based formalisms and network representations. In particular, the role of time in AI formalisms is discussed. Another important related issue, scarcely considered in music research, regards planning and action theories. Furthermore, he discusses the necessity of integrating different formalisms into hybrid systems, to cope with the different complex problems existing in music activities. He emphasizes the importance of this topic showing, as a case study, some design issues on a particular music knowledge representation system.

Musical Representation of Sound in Computer-Aided Composition: A Visual Programming Framework

“…Individually, these elements do not hold any specific meaning for a composer and can hardly be put in relation with one another in the compositional process. We could relate these representations to the subsymbolic domain discussed in Leman (1993) and Camurri (1990) if (with some simplification to the original concept) we consider that this domain brings together processes and representations that carry relevant meanings for the bare computer processing of the data, while symbolic representations hold meaning for the system user (e.g. a composer).…”

A comprehensive overview of AI-enabled music classification and its influence in games

“…To take a look at the performance, the study focuses on controlling the piano with different body gestures by the world's best dancer Kaiji Moriyama. Camurri [10] has performed a survey of the recent development and enhancement in one of the unexplored areas of AI called artificial intelligence and music(AIM). The study explores some of the factors of artificial intelligence, which can significantly improve the existing AI-based music generation work.…”

Cognitive science: A new research program for musicology

“…Further, there is a strong tendency to formulate formal models of musical structure and music perception (Longuet-Higgins 1987; Longuet-Higgins & Lisle 1989; Longuet-Higgins & Steedman 1971) and one is speaking of "effective models" (Smoliar 1976), "computational models" (Camilleri 1986) and the concept of the "turing machine" (Laske 1986); or one is using formalisms for knowledge representation from artificial intelligence Kendall 1987;Camurri 1990) or theoretical computer science and artificial intelligence (Bel 1990(Bel , 1991Kippen 1987Kippen , 1988Kippen & Bel 1989). All these formalisms are used to serve as explication for the underlying representational structures and processes which are involved in music cognition.…”