Research in music and artificial intelligence

Roads, Curtis

doi:10.1145/4468.4469

Cited by 57 publications

(28 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is often claimed that the computational approach to modelling musical styles allows hypotheses to be scientifically evaluated (see e.g., Ames & Domino, 1992;Camilleri, 1992;Laske, 1988;Roads, 1985;Sundberg & Lindblom, 1976. Sometimes, this appears to be associated with the implicit assumption that the formality and precision required of a computer model of itself makes an implemented theory scientific.…”

Section: Discussionmentioning

confidence: 99%

“…As we noted in § 6, this kind of project has sometimes been grouped together with research in the computational modelling of musical styles under the generic rubric generative modelling of music (Roads, 1985). Laske (1988, p. 43) proposes that the object of study in "the new science of cognitive musicology" is "musical intelligence as a distinctive human faculty".…”

Section: Motivationmentioning

confidence: 99%

See 1 more Smart Citation

Motivations and Methodologies for Automation of the Compositional Process

2002

View full text Add to dashboard Cite

Our aim in this paper is to clarify the range of motivations that have inspired the development of computer programs for the composition of music. We consider this to be important since different methodologies are appropriate for different motivations and goals. We argue that a widespread failure to specify the motivations and goals involved has lead to a methodological malaise in music related research. A brief consideration of some of the earliest attempts to produce computational systems for the composition of music leads us to identify four activities involving the development of computer programs which compose music each of which is inspired by different practical or theoretical motivations. These activities are algorithmic composition, the design of compositional tools, the computational modelling of musical styles and the computational modelling of music cognition. We consider these four motivations in turn, illustrating the problems that have arisen from failing to distinguish between them. We propose a terminology that clearly differentiates the activities defined by the four motivations and present methodological suggestions for research in each domain. While it is clearly important for researchers to embrace developments in related disciplines, we argue that research in the four domains will continue to stagnate unless the motivations and aims of research projects are clearly stated and appropriate methodologies are adopted for developing and evaluating systems that compose music.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Motivationmentioning

confidence: 99%

Motivations and Methodologies for Automation of the Compositional Process

2002

View full text Add to dashboard Cite

show abstract

“…Some review both analysis and composition by computer with AI methods (Roads, 1985), while others discuss algorithmic composition from a point of view related to music theory and artistic considerations (Collins, 2009), or from the personal perspective of a composer (Langston, 1989;Dobrian, 1993;Pope, 1995;Maurer, 1999). Some of them provide an in depth and comprehensive view of a specific technique for algorithmic composition, as Anders and Miranda (2011) do for constraint programming, as Ames (1989) does for Markov chains, or as Santos et al (2000) do for evolutionary techniques, while some others are specialized in the comparison between paradigms for computational research on music, as Toiviainen (2000).…”

Section: Motivationmentioning

confidence: 99%

AI Methods in Algorithmic Composition: A Comprehensive Survey

Fernández

Vico

2013

jair

207

113

View full text Add to dashboard Cite

Algorithmic composition is the partial or total automation of the process of music composition by using computers. Since the 1950s, different computational techniques related to Artificial Intelligence have been used for algorithmic composition, including grammatical representations, probabilistic methods, neural networks, symbolic rule-based systems, constraint programming and evolutionary algorithms. This survey aims to be a comprehensive account of research on algorithmic composition, presenting a thorough view of the field for researchers in Artificial Intelligence.

show abstract

“…Major efforts have also been produced in computer music (for a complete survey, see Roads, 1985), while just a few interesting applications can be found in poetry (Davison, 1982;Wilson, 1984), sculpture (Mallory, 1969), computer animation (Kahn, 1979;Zeltzer, 1983;Badler, 1989), and choreography (Stadler, 1982).…”

Section: Introductionmentioning

confidence: 99%

Can you make a computer understand and produce art?

Maiocchi

1991

AI & Soc

View full text Add to dashboard Cite

Although artificial intelligence techniques have been successfully applied to reproduce many rational features of human behaviour, a great barrier has been encountered in simulating human activities where intuition and emotion are involved. Art making and viewing are processes where typically rational and mechanical aspects interact with aesthetic and cognitive criteria. Can you make a computer understand and autonomously produce art?The main purpose of this paper is to present the most relevant approaches in the study of art perception and creation via computer, focusing on the results achieved in artistic computer graphics.

show abstract

Research in music and artificial intelligence

Cited by 57 publications

References 53 publications

Motivations and Methodologies for Automation of the Compositional Process

Motivations and Methodologies for Automation of the Compositional Process

AI Methods in Algorithmic Composition: A Comprehensive Survey

Can you make a computer understand and produce art?

Contact Info

Product

Resources

About