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.

[1]  Maximos A. Kaliakatsos-Papakostas,et al.  Probabilistic harmonization with fixed intermediate chord constraints , 2014, ICMC.

[2]  Maximos A. Kaliakatsos-Papakostas,et al.  A Probabilistic Approach to Determining Bass Voice Leading in Melodic Harmonisation , 2015, MCM.

[3]  Elaine Chew,et al.  A Hybrid System for Automatic Generation of Style-Specific A ccompaniment , 2007 .

[4]  Darrell Conklin,et al.  Representation and Discovery of Vertical Patterns in Music , 2002, ICMAI.

[5]  José Manuel Iñesta Quereda,et al.  Genre classification using chords and stochastic language models , 2009, Connect. Sci..

[6]  Roberto Confalonieri,et al.  An Argument-based Creative Assistant for Harmonic Blending , 2016, ICCC.

[7]  Martin Rohrmeier,et al.  Towards a generative syntax of tonal harmony , 2011 .

[8]  G. Fauconnier,et al.  The Way We Think: Conceptual Blending and the Mind''s Hidden Complexities. Basic Books , 2002 .

[9]  J. Goguen.  Mathematical Models of Cognitive Space and Time , 2006 .

[10]  Maximos A. Kaliakatsos-Papakostas,et al.  An Idiom-independent Representation of Chords for Computational Music Analysis and Generation , 2014, ICMC.

[11]  Rafael Peñaloza,et al.  Upward Refinement for Conceptual Blending in Description Logic: An ASP-based Approach and Case Study in EL++ , 2015, JOWO@IJCAI.

[12]  Maximos A. Kaliakatsos-Papakostas,et al.  Learning and Creating Novel Harmonies in Diverse Musical Idioms: An Adaptive Modular Melodic Harmonisation System , 2016 .

[13]  Mark Steedman.  The Blues and the Abstract Truth: Music and Mental Models , 2009 .

[14]  Kai-Uwe Kühnberger,et al.  COINVENT: Towards a Computational Concept Invention Theory , 2014, ICCC.

[15]  Marco Schorlemmer,et al.  ASP, Amalgamation, and the Conceptual Blending Workflow , 2015, LPNMR.

[16]  Geraint A. Wiggins,et al.  Computational Modeling of Music Cognition and Musical Creativity , 2011 .

[17]  Christopher Raphael,et al.  Functional Harmonic Analysis Using Probabilistic Models , 2004, Computer Music Journal.

[18]  Geraint A. Wiggins,et al.  Multiple Viewpoint Systems: Time Complexity and the Construction of Domains for Complex Musical Viewpoints in the Harmonization Problem , 2013 .

[19]  Emilios Cambouropoulos,et al.  The Harmonic Musical Surface and Two Novel Chord Representation Schemes , 2016, Computational Music Analysis.

[20]  Maximos A. Kaliakatsos-Papakostas,et al.  Structural Blending of Harmonic Spaces : a Computational Approach , 2015 .

[21]  Kai-Uwe Kühnberger,et al.  Concept invention and music: Creating novel harmonies via conceptual blending , 2014 .

[22]  Maximos A. Kaliakatsos-Papakostas,et al.  HARMONY IN THE POLYPHONIC SONGS OF EPIRUS : REPRESENTATION , STATISTICAL ANALYSIS AND GENERATION , 2014 .

[23]  Maximos A. Kaliakatsos-Papakostas,et al.  Conceptual Blending in Music Cadences: A Formal Model and Subjective Evaluation , 2015, ISMIR.

[24]  Ricardo Scholz,et al.  Robust modeling of musical chord sequences using probabilistic N-grams , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[25]  Mark Steedman,et al.  A Robust Parser-Interpreter for Jazz Chord Sequences , 2014 .

[26]  Kai-Uwe Kühnberger,et al.  Computational Invention of Cadences and Chord Progressions by Conceptual Chord-Blending , 2015, IJCAI.

[27]  Maximos A. Kaliakatsos-Papakostas,et al.  Probabilistic Modular Bass Voice Leading in Melodic Harmonisation , 2015, ISMIR.

[28]  Simon Dixon,et al.  Probabilistic and Logic-Based Modelling of Harmony , 2010, CMMR.

[29]  Maximos A. Kaliakatsos-Papakostas,et al.  Evaluating the General Chord Type Representation in Tonal Music and Organising GCT Chord Labels in Functional Chord Categories , 2015, ISMIR.