Title | ||
---|---|---|
ConBreO: a music performance rendering system using hybrid approach of IEC and automated evolution |
Abstract | ||
---|---|---|
This paper presents an IEC (Interactive Evolutionary Computation) system named ConBreO to render expressive music performance using Genetic Programming. The central problem of IEC is the limitation of number of fitness evaluations because of user fatigue. In the system, we introduce two support techniques for IEC. The first one is a hybrid approach of IEC and automated evolution which allows the system to evolve both of IEC and automated evolution. The second one is the selective presentation which selects a new individual to be evaluated by the user based on its expected improvement of fitness. Using the system, obtained expression rule won an award at a performance rendering contest which evaluates computer systems generating expressive musical performances. Our experiment shows that the selective presentation reduces the number of fitness evaluations required to construct the fitness prediction model and prevents the system evaluating unfruitful individuals. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1145/1830483.1830711 | GECCO |
Keywords | Field | DocType |
genetic programming,expressive musical performance,computer system,selective presentation,automated evolution,fitness prediction model,hybrid approach,fitness evaluation,user fatigue,expressive music performance,music performance rendering system,performance rendering contest,interactive evolutionary computation | Interactive evolutionary computation,Computer science,Genetic programming,Artificial intelligence,Rendering (computer graphics),Machine learning | Conference |
Citations | PageRank | References |
0 | 0.34 | 13 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Makoto Tanji | 1 | 5 | 1.26 |
Hitoshi Iba | 2 | 1541 | 138.51 |