基于贝叶斯网研究自动作曲中音高的表示和推理

计算机科学 ›› 2014, Vol. 41 ›› Issue (Z11): 21-24.

基于贝叶斯网研究自动作曲中音高的表示和推理

翁诗杰,李维华,丁海燕

云南大学信息学院计算机科学与技术系昆明650091;云南大学信息学院计算机科学与技术系昆明650091;云南大学信息学院计算机科学与技术系昆明650091

出版日期:2018-11-14 发布日期:2018-11-14

Representing and Reasoning Pitches in Algorithmic Composition Based on Bayesian Networks

WENG Shi-jie,LI Wei-hua and DING Hai-yan

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 自动作曲或称算法作曲是利用计算机进行自动或半自动的音乐创作过程。算法作曲的关键之一是生成音高。然而,不确定性是音乐本身固有的特征。贝叶斯网是不确定性知识的表示和推理的典型工具,已经成功应用到很多领域。在MIDI格式的基础上,利用贝叶斯网在算法作曲中生成音高,首先建立一个关于音高的贝叶斯网模型并基于此模型建立知识库。其次,基于贝叶斯网对音高进行推理,生成给定节拍处的每一个音的音高。实验表明,所提出的音高推理方法是可行的。

关键词: 算法作曲,计算机音乐,MIDI音乐系统,贝叶斯网,推理

Abstract: Algorithmic composition is the partial or total automatic process of music composition by a computer.One of the challenges in algorithmic composition is to create pitches.However,uncertainty is an intrinsic feature of music.Bayesian network (BN) is an effective and popular framework for representing and reasoning knowledge under uncertainty,and BNs have been successfully applied to a variety of problems.Based on MIDI format to create pitches in algorithmic composition,we firstly built a model about pitches with BNs and a knowledge base based on the model.More-over,based on bayesian inference,the pitch of every note at each pat could be created.A preliminary experiment demonstrates empirically that this method for pitch inference is feasible.

Key words: Algorithmic composition,Computer music,MIDI musical system,Bayesian network,Inference

翁诗杰,李维华,丁海燕. 基于贝叶斯网研究自动作曲中音高的表示和推理[J]. 计算机科学, 2014, 41(Z11): 21-24. https://doi.org/

WENG Shi-jie,LI Wei-hua and DING Hai-yan. Representing and Reasoning Pitches in Algorithmic Composition Based on Bayesian Networks[J]. Computer Science, 2014, 41(Z11): 21-24. https://doi.org/

参考文献

[1] 冯寅,周昌乐.算法作曲的研究进展[J].软件学报,2006,7(2):209-215
[2] Tromp M,Bod R,Honingh A.Learning Symbolic Music through Hidden Markov Model Induction[J].2012
[3] Fernández J D,Vico F.AI methods in algorithmic composition:a comprehensive survey[J].Journal of Artificial Intelligence Research,2013,8(1):513-82
[4] Bell C.Algorithmic music composition using dynamic Markovchains and genetic algorithms[J].Journal of Computing Sciences in Colleges,2011,7(2):99-107
[5] Salas H A G,Gelbukh A,Calvo H.Music composition based on linguistic approach[M]∥Advances in Artificial Intelligence.Springer,2010:117-128
[6] Boutsinas C,Ha B.Automatic interactive music improvisationbased on data mining[J].International Journal on Artificial Intelligence Tools,2012,1(4):1-24
[7] Khan A H.Artificial intelligence approaches to music composition[D].Northern Kentucky University,2013
[8] Edwards M.Algorithmic composition:computational thinking in music[J].Communications of the ACM,2011,4(7):58-67
[9] Donnelly P,Sheppard J.Evolving four-part harmony using genetic algorithms[M]∥Applications of Evolutionary Computation.Springer,2011:273-82
[10] Morone A,Manzolli J,Von Zuben F,et al.Evolutionary Computation applied to Algorithmic Composition[J].NICS Reports,2013(3):49-53
[11] c′ D.A genetic algorithm for composing music[J].Yugoslav Journal of Operations Research,2013,0(1):2334-6043
[12] Kirke A,Miranda E R.A survey of computer systems for expressive music performance[J].ACM Computing Surveys (CSUR),2009,2(1):3
[13] 刘惟一,李维华,岳昆.智能数据分析[M].北京:科学出版社,2007
[14] Raphael C,et al.A Bayesian Network for Real-Time Musical Accompaniment[M]∥Advances in Neural Information Proces-sing Systems.2002
[15] Oyen D,Lane T,et al.Leveraging Domain Knowledge in Multitask Bayesian Network Structure Learning[C]∥AAAI.2012
[16] 李金鑫.计算机自动混音系统设计——面向自动作曲系统MIDI 表达的实现[J].电脑编程技巧与维护,2010(14):104-1055
[17] 曹西征,毛文涛,乔锟,等.基于音高旋律元的柔和乐曲的自动作曲算法[J].自动化学报,2012,8(10):1627-1638
[18] Povel D-J.Melody generator:A device for algorithmic musicconstruction[J].Journal of Software Engineering and Applications,2010,3(7):683

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed