Improvement in Diversity of Music Composed by the Automatic Composition System Adapting the Personal Sensibility

2022 Fiscal Year Final Research Report

• Project/Area Number: 17K00390
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Kansei informatics
• Research Institution: Tokyo City University
• Principal Investigator: Otani Noriko 東京都市大学, メディア情報学部, 教授 (70328566)
• Project Period (FY): 2017-04-01 – 2023-03-31
• Keywords: 自動作曲 / 進化計算アルゴリズム / 感性モデル

Outline of Final Research Achievements

In this study, we proposed a method for automatically generating various musical pieces that reflect personal sensibilities, with the aim of satisfying the need for musical composition in various situations. The methods for generating musically superior pieces, such as determining the pitch of melodies, determining how to play chord progressions, and generating preludes and postludes, were developed. The methods were also developed to generate pieces for various genres and purposes, including classical ballet lessons, progressive house pieces, piano practice pieces as an alternative to Hanon, and performance-oriented electric organ pieces. In addition, we also participated in practical activities such as the AI Lullaby Project of Toho and Alphapolis, the "AI Beethoven" concert sponsored by the COI of Tokyo University of the Arts, and the creation of a sound logo for the corporate name of Fukoku Mutual Life Insurance Company.

Free Research Field

進化計算アルゴリズム

Academic Significance and Societal Importance of the Research Achievements

本研究の成果は，自分の創作意図の表現や鑑賞者の感性への訴えかけに効果的な楽曲を自身の作品に付与したい制作者，自分の感性に触れる楽曲を求める聴者，および普段から作曲を手がけているアーティストに対し，それぞれの目的に応じた楽曲を大きな負担を負うことなく次々と生成する手段を提供するものである．また，本研究で参画した実践的な取組みは，自動作曲技術の多様な応用可能性を示唆するものである．