Download presentation
Presentation is loading. Please wait.
1
On Algorithmic Representation of Music Style David Cope Professor of Music, Univ. of California, Santa Cruz
2
Overview EMI (Experiments in Music Intelligence): represent music styles based on linguistic principles Language Parsing Augmented Transition Networks (ATN) Non-linear composition Future work
3
Language Parsing Emphasis: hierarchy (most to least important) and abstraction of function Ex. I am driving to the country. I am driving the country. I am driving to the ( ). I country.
4
Language Parsing (cont.) Hierarchical Parsing (Arrow: logical modifier processions) Abstraction of function
5
Musical Parallels Schenkerian layer analysis: prolongation of tonic from the first to the last C Hierarchical Parsing
6
Music Parallels (cont.) Abstraction of function EMI Symbology: OSAC (identifiers, priority order) O: ornamental S: statement A: antecedent C: consequent Level of importance: 1-3 (least to most significant )
7
Augmented Transition Networks (ATN) Allow finer detail between context-free and context driven environments
8
ATN (cont.) Music example
9
Non-linear Composition Top-down method Music has an end. Mid-level communication No backtracking
10
Example A Back-like keyboard invention
11
Future Works Refine ATN engine More accurate representations of style integrity
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.