以音高類集為理論基礎的自動作曲研究

A Study on the Pitch-Class Set Based Automated Composition

柯舒方(Shu-Fang Ko)

指導教授 ： 黃志方 ； 成維華

國立交通大學/工學院/聲音與音樂創意科技碩士學位學程/碩士(2011年)

https://doi.org/10.6842/NCTU.2011.00657

摘要

本論文為以音高類集為理論基礎的自動作曲研究，自動作曲是利用電腦產生符合樂理規則的音樂，我們根據樂理或經驗來產生自動作曲的規則。在結構部分，加入動機變化與主題發展的功能，節奏產生則使用節奏複雜度來增加節奏的組合性，音高部分使用音高類集理論來創作，系統提供調性音樂及非調性音樂的樂曲產生，在調性音樂產生中，除了符合基本 24 個大小調的特性外，更加入終止式來加強調性音樂的和聲結構。本次研究的實驗結果，在調性辨識率上，調性辨識率平均為 78.25% ，非調性的調性辨識率平均為 52.75%；在動機變化程度及喜好程度方面，我們使用 Likert 5-point Scale 的方法來計算分數，動機變化程度整體平均分數為 3.5 ，在水準之上；喜好程度比例依照調性音樂及非調性音樂各為 3.29 及 2.66 ，顯示大部分受試者對於調性音樂的接受度比較高。

關鍵字

自動作曲 ； 演算法作曲 ； 音高類集 ； 節奏複雜度 ； 動機與主題發展

並列摘要

This thesis is based on Pitch Class Set theory to do the automated composition research. Automated composition can generate music applying music theory and rules with experiences into the generative music system. As to the music structure, motif variation and thematic development function is added. Rhythm generation can be performed by the rhythm combination with rhythm complexity. Pitch generation is
based on the pitch class set theory to compose, and both tonal and atonal music patterns can be provided by the system automatically. Tonal music generation not only supports 24 major/minor keys, but also integrates the harmonic cadence implicitly. The experiment result shows the tonal music identification rate for the subjects is 78.25%, and the atonal music identification rate is 52.75%. With 5-point Likert scale, motive variation identification rate for listeners is 3.44 in average, and the generative music preference level is 3.29 and 2.66 for tonal and atonal music respectively, which shows that most people would prefer to accept tonal music, rather than atonal music.

並列關鍵字

Automated Composition ； Algorithmic Composition ； Pitch Class Set ； Rhythm Complexity ； Motif and Thematic Development

參考文獻

[1] Ames, C., “The Markov Process as a Compositional Model: A Survey and Tutorial”, Leonardo, vol. 22, no. 2, pp. 175—187, 1989.

[6] Povel, D.J., “Melody Generator: A Device for Algorithmic Music Construction”, Journal of Software Engineering & Applications, 3, 683-695, 2010.

[7] Temperley, D., “A Probabilistic Model of Melody Perception”, Cognitive Science, vol.32, no.2, pp418—444, 2008.

[10] Schuijer, M., Analyzing Atonal Music: Pitch-Class Set Theory and Its Contexts, Eastman Studies in Music 60. Rochester, NY: University of Rochester Press, 2008.

[13] Stein, L.: Structure & Style: The Study and Analysis of Musical Forms, Summy-Birchard Music, 1979.