Costas Tsougras

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.

Conceptual Blending of Harmonic Spaces for Creative Melodic Harmonisation

AbstractIn computational creativity, new concepts can be invented through conceptual blending of two independent conceptual spaces. In music, conceptual blending has been primarily used for analysing relations between musical and extra-musical elements in composed music rather than generating new music. This paper presents a probabilistic melodic harmonisation assistant that employs conceptual blending to combine learned, potentially diverse, harmonic idioms and generate new harmonic spaces that can be used to harmonise melodies given by the user. The key feature of this system is the application of creative conceptual blending to the most common chord transitions (pairs of consecutive chords) of two initial harmonic idioms. The proposed methodology integrates newly created blended chords and transitions in a compound probabilistic harmonic space, that preserves combined characteristics from both initial idioms along with those new chords and transitions within a unified setting. This methodology enables ...

The Application of GTTM on 20th Century Modal Music: Research Based on the Analysis of Yannis Constantinidis's “44 Greek Miniatures for Piano”

This paper examines the adaptation and expansion of Lerdahl’ s & Jackendoff s Generative Theory of Tonal Music so that it may be applied on the analysis of 20th century modal music. Based on the premise that a considerable part of the theorys rules are universal — meaning that the principles of music perception and cognition are the same for all experienced listeners regardless of the musical idiom in which they are experienced — the application of GTTM to musical idioms other than the Western classical one requires formulation of idiom-specific well-formedness and preference rules, and description of the special tonal hierarchy. These tasks may be accomplished through the analytical study of a considerable quantity of music representing a certain idiom, and the description of its features in relation to the four parts of the GTTM methodology. The chosen analytical object — 44 Greek miniatures for piano — is representative of the musical idiom deriving from the amalgamation of Greek modal music and 20th century harmonization techniques, distinctive of the musical style of Greek composer Yannis Constantinidis. An inductive methodological process was used for the individual and comparative analysis of all 44 pieces. This paper includes three complete GTTM sample analyses from the 44 piano pieces, a summary of the stylistic characteristics of the analyzed music, and the formulation of the special well-formedness and preference rules, introduced as either new rules to the theory or adaptations of the existing ones.

Modal Pitch Space — A Theoretical and Analytical Study

This paper presents an approach to the pitch space of the seven diatonic modes. The proposed theory is an expansion of Fred Lerdahls tonal pitch space model; its purpose is a more accurate description of the situations involved in the analysis of diatonic modal music. The original methodology and set of algebraic calculating formulae is retained, but it is applied on modal instead of tonal space, on the basis that the latter is a subset of the former. In connection to Fred Lerdahls theory, melodic motion, chord attraction and various cadence types are described within the modal context. Apart from the calculation of the pitch and the chordal and regional space algebraic representations, geometrical representations of all three levels of the modal pitch space are also included. Finally, the stability conditions arising from the new model are used as criteria to build the time span reduction and prolongational reduction parts of the Generative Theory of Tonal Music (GTTM) analysis of modal music. Two short GTTM analyses of 20th century modal music are being presented to illustrate the new models analytical use.

Musical blending and creativity: An empirical evaluation of the CHAMELEON melodic harmonisation assistant

This article presents the CHAMELEON melodic harmonisation assistant that utilises the principles of conceptual blending theory as a means for the invention of hybrid or novel harmonic idioms and an empirical evaluation of a number of computer-generated melodic harmonisation blends. Melodies originating from various idioms were harmonised either according to the harmonic rules of the original idiom, according to the rules of a different idiom (melody–harmony blends), or by blending idioms, modes and transported versions of the same idiom (harmony–harmony blends). In two similar experimental set ups, the task of the listeners was to i) perform idiom, mode or type of chromaticism classification, ii) report their preference, and iii) rate the degree of expectancy characterising each harmonisation. The results show that harmonic blending (either melody–harmony or harmony–harmony) influences the identification of idiom, mode and type of chromaticism. This suggests that the harmonic blending system has indeed succeeded in producing perceivable blends under various conditions that were unexpected and also equally preferred compared to non-blends.

Embedded blends and meaning construction in Modest Musorgsky’s Pictures at an Exhibition

Conceptual blending is a cognitive theory positing the combination of diverse conceptual spaces for the creation of novel blended spaces. Musical conceptual blending can be intra-musical, pertaining to the combination of diverse structural elements for the creation of new melodies, harmonies or textures, as well as cross-domain, involving the integration of musical and non-musical spaces for the creation of novel analogies or metaphors. This article presents a structural and hermeneutical analysis of “Il vecchio castello” and “Samuel Goldenberg und Schmuÿle” from Modest Musorgsky’s Pictures at an Exhibition in an attempt to disclose both the intra-musical (combination of modal, tonal or coloristic harmonic spaces and rhythmic/textural structure) and extra-musical (contextual, symbolic and programmatic aspects) conceptual blending that the works incorporate. The reductional/prolongational analyses provide input for two distinct Conceptual Integration Networks, the first describing the intra-musical blending of melodic harmonization and the second proposing the cross-domain blending of the musical and pictorial input spaces into a blended hermeneutical space that projects the works’ narrative/programmatic/emotional potential. The proposed analyses show how musical structure promotes creative listening and meaning construction through complex cross-domain integration. This research suggests that conceptual blending theory as an analytical tool can promote a richer structural interpretation and experience of music, even in cases of instrumental, non-vocal compositions.

Modelling Cadence Perception Via Musical Parameter Tuning to Perceptual Data

Conceptual blending when used as a creative tool combines the features of two input spaces, generating new blended spaces that share the common structure of the inputs, as well as different combinations of their non-common parts. In the case of music, conceptual blending has been employed creatively, among others, in generating new cadences (pairs of chords that conclude musical phrases). Given a specific set of input cadences together with their blends, this paper addresses the following question: are some musical features of cadences more salient than others in defining perceived relations between input and blended cadences? To this end, behavioural data from a pairwise dissimilarity listening test using input and blended cadences as stimuli were collected, thus allowing the construction of a ‘ground-truth’ human-based perceptual space of cadences. Afterwards, the salience of each cadence feature was adjusted through the Differential Evolution (DE) algorithm, providing a system-perceived space of cadences that optimally matched the ground-truth space. Results in a specific example of cadence blending indicated that some features were distinguishably more salient than others. This pilot study was a first step towards building self-aware blending systems and revealed that the salience of features in conceptual blending is an essential part for producing perceptually relevant blends.