A Genetic Rule-Based Model of Expressive Performance for Jazz Saxophone
A Genetic Rule-Based Model of Expressive Performance for Jazz Saxophone
复制标题
基于遗传规则的爵士萨克斯表现力模型
DOI：
10.1162/comj.2008.32.1.38
复制
发表时间：
2008
影响因子：
--
通讯作者：
Xavier Serra
中科院分区：
文献类型：
--
作者：
R. Ramírez;Amaury Hazan;Esteban Maestre;Xavier Serra
已经提出了38个使用进化技术来生成音乐作品的计算机音乐期刊系统，包括元胞自动机音乐(Millen 1990)、元胞自动机音乐工作站(Hunt、Kirk和Orton 1991)、Camus(Miranda 1993)、Moe(Degazio 1999)、GenDash(Waschka 1999)、Camus 3D(Mc阿尔卑斯、Miranda和Hogar 1999)、Vox Popoli(Manzolli等人)。主要作品有：合成和声(Bilotta、Pantano和Talarico 2000)、活生生的旋律(Dahlstedt和Nordhal 2001)和Genphone(Mandelis 2001)。基于遗传算法的作曲系统通常遵循标准的遗传算法方法来进化音乐材料，例如旋律、节奏和和弦。因此，这样的组成系统与本文介绍的系统共享核心方法。例如，Vox Popoli(Manzolli等人)。1999)进化了四个音符的和弦的种群，每个音符被表示为七位字符串。因此，和弦的基因由一个28位的字符串组成，并对这些字符串进行交叉和突变的遗传操作，以产生新一代的种群。适应度函数基于三个标准：旋律适应度、和声适应度和音域适应度。通过将和弦的音符与用户提供的参考值进行比较来评估旋律适合度；和声适合度考虑和弦的和声；以及音域适合度测量和弦的音符是否在也由用户指定的范围内。进化计算也被考虑用于即兴演奏应用(Biles 1994)，其中开发了一个基于遗传算法的新手爵士乐演奏家学习即兴演奏的模型。该系统演变了一组旋律想法，这些想法被映射到音符中，考虑到正在演奏的和弦进程。适应度函数可以通过玩弄系统的人的反馈来改变。然而，将进化计算用于表达性能分析的工作还很少。在ProMusic项目的背景下，Grachten等人(2004)通过遗传算法优化了编辑距离操作的权重，以注释人类爵士乐表演。它们提供了基于编辑距离的音乐演奏注释的增强。为了减少自动性能标注中的错误次数，他们使用进化方法来优化编辑距离的代价函数的参数值。在另一项研究中，Hazan等人(2006)提出了一种用于MIDI性能的表现性渲染的进化生成回归树模型。Madsen和Widmer(2005)提出了一种探索古典钢琴演奏相似性的方法，该方法基于对舒伯特钢琴作品的12段录音的时间和强度的简单测量。本文介绍的工作是我们以前工作(Ramirez和Hazan 2005)的扩展，在该工作中，我们使用遗传算法来归纳表现力-表现分类规则。在这里，除了考虑分类规则外，我们还考虑了回归规则，而在Ramirez和Hazan中，规则是由遗传算法独立归纳的，这里我们应用了一种序列覆盖算法来覆盖整个示例空间。
38 Computer Music Journal systems using evolutionary techniques to generate musical compositions have been proposed, including Cellular Automata Music (Millen 1990), a Cellular Automata Music Workstation (Hunt, Kirk, and Orton 1991), CAMUS (Miranda 1993), MOE (Degazio 1999), GenDash (Waschka 1999), CAMUS 3D (McAlpine, Miranda, and Hogar 1999), Vox Populi (Manzolli et al. 1999), Synthetic Harmonies (Bilotta, Pantano, and Talarico 2000), Living Melodies (Dahlstedt and Nordhal 2001), and Genophone (Mandelis 2001). Composition systems based on genetic algorithms generally follow the standard genetic-algorithm approach for evolving musical materials such as melodies, rhythms, and chords. As a result, such compositional systems share the core approach with the one presented in this article. For example, Vox Populi (Manzolli et al. 1999) evolves populations of chords of four notes, each of which is represented as a seven-bit string. The genotype of a chord therefore consists of a string of 28 bits, and the genetic operations of crossover and mutation are applied to these strings to produce new generations of the population. The fitness function is based on three criteria: melodic fitness, harmonic fitness, and voice-range fitness. The melodic fitness is evaluated by comparing the notes of the chord to a reference value provided by the user; the harmonic fitness takes into account the consonance of the chord; and the voice-range fitness measures whether the notes of the chord are within a range also specified by the user. Evolutionary computation has also been considered for improvisation applications (Biles 1994), where a genetic algorithmbased model of a novice jazz musician learning to improvise was developed. The system evolves a set of melodic ideas that are mapped into notes considering the chord progression being played. The fitness function can be altered by the feedback of the human playing with the system. Nevertheless, few works focusing on the use of evolutionary computation for expressiveperformance analysis exist. In the context of the ProMusic project, Grachten et al.(2004) optimized the weights of edit-distance operations by a genetic algorithm to annotate a human jazz performance. They present an enhancement of edit-distance-based music-performance annotation. To reduce the number of errors in automatic-performance annota-tion, they use an evolutionary approach to optimize the parameter values of cost functions of the edit distance. In another study, Hazan et al.(2006) proposed an evolutionary generative regression-tree model for expressive rendering of MIDI perfor-mances. Madsen and Widmer (2005) present an approach exploring similarities in classical piano performances based on simple measurements of timing and intensity in 12 recordings of a Schubert piano piece. The work presented in this article is an extension of our previous work (Ramirez and Hazan 2005), where we induce expressive-performance classification rules using a genetic algorithm. Here, in addition to considering classification rules, we consider regression rules, and whereas in Ramirez and Hazan, rules are independently induced by the genetic algorithm, here we apply a sequential-covering algorithm to cover the whole example space.