Maximos A. Kaliakatsos-Papakostas

evoDrummer: deriving rhythmic patterns through interactive genetic algorithms

Drum rhythm automatic construction is an important step towards the design of systems which automatically compose music. This work describes a novel mechanism that allows a system, namely the evoDrummer, to create novel rhythms with reference to a base rhythm. The user interactively defines the amount of divergence between the base rhythm and the generated ones. The methodology followed towards this aim incorporates the utilization of Genetic Algorithms and allows the evoDrummer to provide several alternative rhythms with specific, controlled divergence from the selected base rhythm. To this end, the notion of rhythm divergence is also introduced, based on a set of 40 drum---specific features. Four population initialization schemes are discussed and an extensive experimental evaluation is provided. The obtained results demonstrate that, with proper population initialization, the evoDrummer is able to produce a great variety of rhythmic patterns which accurately encompass the desired divergence from the base rhythm.

Genetic evolution of L and FL-systems for the production of rhythmic sequences

Music composition with algorithms inspired by nature has led to the creation of systems that compose music with rich characteristics. Nevertheless, the complexity imposed by unsupervised algorithms may arguably be considered as undesired, especially when considering the composition of rhythms. This work examines the composition of rhythms through L and Finite L-systems (FL-systems) and presents an interpretation from grammatical to rhythmic entities that expresses the repetitiveness and diversity of the output of these systems. Furthermore, we utilize a supervised training scheme that uses Genetic Algorithms (GA) to evolve the rules of L and FL-systems, so that they may compose rhythms with certain characteristics. Simple rhythmic indicators are introduced that describe the density, pauses, self similarity, symmetry and syncopation of rhythms. With fitness evaluations based on these indicators we assess the performance of L and FL-systems and present results that indicate the superiority of the FL-system in terms of adaptability to certain rhythmic tasks.

Controlling interactive evolution of 8-bit melodies with genetic programming

Automatic music composition and sound synthesis is a field of study that gains continuously increasing attention. The introduction of evolutionary computation has further boosted the research towards exploring ways to incorporate human supervision and guidance in the automatic evolution of melodies and sounds. This kind of human–machine interaction belongs to a larger methodological context called interactive evolution (IE). For the automatic creation of art and especially for music synthesis, user fatigue requires that the evolutionary process produces interesting content that evolves fast. This paper addresses this issue by presenting an IE system that evolves melodies using genetic programming (GP). A modification of the GP operators is proposed that allows the user to have control on the randomness of the evolutionary process. The results obtained by subjective tests indicate that the utilization of the proposed genetic operators drives the evolution to more user-preferable sounds.

Intelligent Generation of Rhythmic Sequences Using Finite L-systems

Algorithmic music synthesis with intelligent methodologies is a subject of research under both unsupervised and supervised forms, with the production of rhythm being an important aspect of the compositional process. Unsupervised algorithms tend to produce rhythms that are described either as simplistic and repetitive, or very complex and unstable. This work examines a modification of the legacy L-systems that are hereby termed as Finite L-systems (FL-systems). With this modification, the produced symbolic sequences are more controllable, offering a rhythm production alternative that is more flexible than the L-systems. In particular, when used for unsupervised rhythm production, FL-systems construct rhythmic sequences with great variability in terms of complexity and repetitiveness. This trend indicates that their combination with learning algorithms may provide a flexible supervised rhythm production system.

Musical composer identification through probabilistic and feedforward neural networks

During the last decade many efforts for music information retrieval have been made utilizing Computational Intelligence methods. Here, we examine the information capacity of the Dodecaphonic Trace Vector for composer classification and identification. To this end, we utilize Probabilistic Neural Networks for the construction of a “similarity matrix” of different composers and analyze the Dodecaphonic Trace Vectors ability to identify a composer through trained Feedforward Neural Networks. The training procedure is based on classical gradient-based methods as well as on the Differential Evolution algorithm. An experimental analysis on the pieces of seven classical composers is presented to gain insight about the most important strengths and weaknesses of the aforementioned approach.

Interactive evolution of 8---bit melodies with genetic programming towards finding aesthetic measures for sound

The efficient specification of aesthetic measures for music as a part of modelling human conception of sound is a challenging task and has motivated several research works. It is not only targeted to the creation of automatic music composers and raters, but also reinforces the research for a deeper understanding of human noesis. The aim of this work is twofold: first, it proposes an Interactive Evolution system that uses Genetic Programming to evolve simple 8---bit melodies. The results obtained by subjective tests indicate that evolution is driven towards more user---preferable sounds. In turn, by monitoring features of the melodies in different evolution stages, indications are provided that some sound features may subsume information about aesthetic criteria. The results are promising and signify that further study of aesthetic preference through Interactive Evolution may accelerate the progress towards defining aesthetic measures for sound and music.

A Probabilistic Approach to Determining Bass Voice Leading in Melodic Harmonisation

Melodic harmonisation deals with the assignment of harmony (chords) over a given melody. Probabilistic approaches to melodic harmonisation utilise statistical information derived from a training dataset to harmonise a melody. This paper proposes a probabilistic approach for the automatic generation of voice leading for the bass note on a set of given chords from different musical idioms; the chord sequences are assumed to be generated by another system. The proposed bass voice leading (BVL) probabilistic model is part of ongoing work, it is based on the hidden Markov model (HMM) and it determines the bass voice contour by observing the contour of the melodic line. The experimental results demonstrate that the proposed BVL method indeed efficiently captures (in a statistical sense) the characteristic BVL features of the examined musical idioms.

Intelligent Real-Time Music Accompaniment for Constraint-Free Improvisation

Computational Intelligence encompasses tools that allow the fast convergence and adaptation to several problems, a fact that makes them eligible for real-time implementations. The paper at hand discusses the utilization of intelligent algorithms (i.e. Differential Evolution and Genetic Algorithms) for the creation of an adaptive system that is able to provide real-time automatic music accompaniment to a human improviser. The main goal of the presented system is to generate accompanying music based on the local human musicians tonal, rhythmic and intensity playing style, incorporating no prior knowledge about the improvisers intentions. Compared to existing systems previously proposed, this work introduces a constraint-free improvisation environment where the most important musical characteristics are automatically adapted to the human performers playing style, without any prior information. This fact allows the improviser to have maximal control over the tonal, rhythmic and intensity improvisation directions.

Combining LSTM and Feed Forward Neural Networks for Conditional Rhythm Composition

Algorithmic music composition has long been in the spotlight of music information research and Long Short-Term Memory (LSTM) neural networks have been extensively used for this task. However, despite LSTM networks having proven useful in learning sequences, no methodology has been proposed for learning sequences conditional to constraints, such as given metrical structure or a given bass line. In this paper we examine the task of conditional rhythm generation of drum sequences with Neural Networks. The proposed network architecture is a combination of LSTM and feed forward (conditional) layers capable of learning long drum sequences, under constraints imposed by metrical rhythm information and a given bass sequence. The results indicate that the role of the conditional layer in the proposed architecture is crucial for creating diverse drum sequences under conditions concerning given metrical information and bass lines.

Learning and Blending Harmonies in the Context of a Melodic Harmonisation Assistant

How can harmony in diverse idioms be represented in a machine learning system and how can learned harmonic descriptions of two musical idioms be blended to create new ones? This paper presents a creative melodic harmonisation assistant that employs statistical learning to learn harmonies from human annotated data in practically any style, blends the harmonies of two user-selected idioms and harmonises user-input melodies. To this end, the category theory algorithmic framework for conceptual blending is utilised for blending chord transition of the input idioms, to generate an extended harmonic idiom that incorporates a creative combination of the two input ones with additional harmonic material. The results indicate that by learning from the annotated data, the presented harmoniser is able to express the harmonic character of diverse idioms in a creative manner, while the blended harmonies extrapolate the two input idioms, creating novel harmonic concepts.