Making Complex Music with Simple Algorithms, is it Even Possible?

Algorithmic composition is often limited to score generation, but may also include sound production. All levels from sound synthesis to the generation of a complete composition can be integrated into one monolithic program. A strict separation of the low level of sound synthesis and higher levels otherwise reserved for algorithmic composition is not necessary, information can flow between all levels. An interesting challenge in this kind of thorough algorithmic composition is to generate as complex music as possible with as little code as possible. The challenge has been accepted, successfully or not, in a series of compositions called Kolmogorov Variations. We discuss the techniques used in a few of the pieces as well as the promises and perils of this strict approach to algorithmic composition.

Research on the Algorithm System for Generation and Creation by Computer Artificial Intelligence and Support Vector Machine

Algorithmic composition is also called automated composition. It is an attempt to use a specific form of process. Composers make full use of computers to carry out music creation and reduce their access. In this paper, based on the standard support vector machine (SVM) learning neural network, the least square support vector machine (LS-SVM) is combined with the recurrent neural network, and a new least square support vector machine learning neural network is proposed. The article realizes the efficient end-to-end multi-dimensional sound wave time series generation model Music-coder, through which the music style music of the famous singer Jay Chou is generated, and the quantified similarity with the real Jay Chou music data set reaches a maximum of 97.73%. The project in this paper shows that intelligent algorithm as a composition tool for music generation and creation is an effective music production program and will bring new development to music production.

On Composers and Computers

The chapter describes the manifold interactions between composers and computers in the creative process. Over time, this dialogue dating back to the 1950s has transcended the paradigm of the traditional compositional process and lead to a number of interesting implications and side effects in the context of current trends in algorithmic composition, generative music, and computational creativity. It is not just the computer but also the choice of software and a specific view on the musical material that are the decisive factors in generative and analytical approaches (which are often interlinked), where strategies of musical representation and the choice of a particular mapping are of crucial importance. Finally, the chapter examines how creativity can be defined and located in this interaction between human and machine.

Representations, Affordances, and Interactive Systems

The history of algorithmic composition using a digital computer has undergone many representations—data structures that encode some aspects of the outside world, or processes and entities within the program itself. Parallel histories in cognitive science and artificial intelligence have (of necessity) confronted their own notions of representations, including the ecological perception view of J.J. Gibson, who claims that mental representations are redundant to the affordances apparent in the world, its objects, and their relations. This review tracks these parallel histories and how the orientations and designs of multimodal interactive systems give rise to their own affordances: the representations and models used expose parameters and controls to a creator that determine how a system can be used and, thus, what it can mean.

Efficient Algorithmic Music Composition Using Neural Networks

Creating aesthetically pleasing music via algorithmic composition has continually been an ambitious goal of music research. Memory-based neural networks have shown to be particularly suited for this type of sequential learning. Music scores data is commonly used to represent different music features–such as durations and pitches–which when combined, make up the entirety of a music piece. As more music features are integrated into the music composition process, the space of labels required to represent possible feature combinations in a neural network grows significantly and rather quickly making the process computationally challenging, to say the least. This consideration bears special importance in situations with polyphonic pieces, where additional features such as harmonies and multiple voices are present. This research highlights the potential benefits of feature separation in music composition from music scores data. More specifically, we demonstrate the effectiveness of neural networks for automated music composition by learning music features separately; we start by creating separate simple models, one for each desired music feature, and then combine results from the simple models to compose new music. This is in contrast to the common practice of employing a single complex model trained over multiple features simultaneously. Case study evaluation results show significant time savings for our proposed approach with similar music “quality” compared to the complex model.

The writing technique as a component of the compositional process (on the examples of creative practice of the second half of the 20th – 21st centuries)

Background, objectives and methodology of the research. The social and cultural paradigm of the 20th century has given rise to a type of composing thinking that did not exist before – a scientific one. Thus, the evolution of the composer’s writing can be defined as a path from thinking by perfect consonance, emancipated dissonance to thinking by deterministic sound and its parameters (height, duration, dynamics, timbre, and articulation). The term of the «composer’s writing technique» means a set of techniques and methods of working with the musical material as a result of the activity of thinking/awareness. Therefore, the aim of this article is an attempt to explore the relationship between the compositional process and writing techniques of the 20th – 21st centuries (pointillism, aleatorysonorous, algorithmic composition), as well as the specifics of polyphonic, homophonic writing in a new context. The methodology of the study includes references to the scientific works by P. Boulez (1971), K. Stockhausen (1963), V. Medushevsky (1984), M. Bonfeld (2006), I. Beckman (2010), I. Kuznetsov (2011), K. Maidenberg-Todorova (2013), M. Vysotska and G. Grigoryeva (2014). Presentation of research results. The phenomenon of writing techniques is very important in the study of the specifics of the compositional process, as it is the technique, for the most part, becomes the goal of creation for many composers of the 20th century. In addition to new techniques, polyphonic and homophonic writing have undergone some changes. The polyphonic one has specific features that are manifested in linearity, part-writing, etc. Examples can be found in the works by D. Ligeti (micro-polyphony), R. Shchedrin, V. Bibik, V. Ptushkin, V. Sylvestrov, and O. Shchetynsky. Regarding the homophonic writing, we shall note that, first of all, it is an indicator of style and conceptual thinking of a composer (works by A. Pyart, J. Tavener, and L. Sumera). In pointillism, the sound is thought of as a deterministic, isolated structure, which is expressed by its various parameters. Here are the examples from the creative work by A. Webern («The Variations for the Piano»; «The Variations for the Orchestra»), by E. Denysov «DSCH». The aleatory-sonorous technique is associated with the operation of timbre sonorities, according to their specific patterns, and developed in the 50–60s of the 20th century in the works by I. Xenakis, V. Lyutoslavsky, Ksh. Penderetsky, and D. Ligeti. The algorithmic composition is an indicator of scientific and mathematical thinking, and is divided into: fractal, stochastic, spectral, concrete and electroacoustic music. The first was formed within the framework of the works by C. Dodge, G. li Nelson, D. Ligeti, and others (I. Beckman, 2010). Stochastic music is associated with the name of I. Xenakis, and the ancestors of the spectral school are the French composers G. Grisey and T. Murray. Conclusions. The article considers the writing techniques of the 20th–21st centuries as components of the compositional process. It can be concluded that the studied techniques are fundamentally interconnected, revealing the nature of the composer’s thinking/consciousness from different positions. The presented techniques are: the objectification of sound forms, the method of creation; the fact of the composer’s consciousness; the consequence of the historical and cultural evolution of the musical language and communication.

Stylistic Composition of Melodies Based on a Brain-Inspired Spiking Neural Network

Current neural network based algorithmic composition methods are very different compared to human brain's composition process, while the biological plausibility of composition and generative models are essential for the future of Artificial Intelligence. To explore this problem, this paper presents a spiking neural network based on the inspiration from brain structures and musical information processing mechanisms at multiple scales. Unlike previous methods, our model has three novel characteristics: (1) Inspired by brain structures, multiple brain regions with different cognitive functions, including musical memory and knowledge learning, are simulated and cooperated to generate stylistic melodies. A hierarchical neural network is constructed to formulate musical knowledge. (2) Biologically plausible neural model is employed to construct the network and synaptic connections are modulated using spike-timing-dependent plasticity (STDP) learning rule. Besides, brain oscillation activities with different frequencies perform importantly during the learning and generating process. (3) Based on significant musical memory and knowledge learning, genre-based and composer-based melody composition can be achieved by different neural circuits, the experiments show that the model can compose melodies with different styles of composers or genres.