Expressive Performance Rendering with Probabilistic Models

We present YQX, a probabilistic performance rendering system based on Bayesian network theory. It models dependencies between score and performance and predicts performance characteristics using information extracted from the score. We discuss the basic system that won the Rendering Contest RENCON 2008 and then present several extensions, two of which aim to incorporate the current performance context into the prediction, resulting in more stable and consistent predictions. Furthermore, we describe the first steps towards a multilevel prediction model: Segmentation of the work, decomposition of tempo trajectories, and combination of different prediction models form the basis for a hierarchical prediction system. The algorithms are evaluated and compared using two very large data sets of human piano performances: 13 complete Mozart sonatas and the complete works for solo piano by Chopin.

[1]  Guerino Mazzola,et al.  The Topos of Music: Geometric Logic of Concepts, Theory, and Performance , 2002 .

[2]  Biing-Hwang Juang,et al.  Hidden Markov Models for Speech Recognition , 1991 .

[3]  Emilia Gómez,et al.  Understanding expressive transformations in saxophone jazz performances using inductive machine learning , 2004 .

[4]  T. Suzuki,et al.  The Second Phase Development of Case Based Performance Rendering System "Kaguramae" , 2003, IJCAI 2003.

[5]  Gerhard Widmer,et al.  Computational Models of Expressive Music Performance: The State of the Art , 2004 .

[6]  Gerhard Widmer,et al.  Machine Discoveries: A Few Simple, Robust Local Expression Principles , 2002 .

[7]  Leonard B. Meyer.  Emotion and Meaning in Music , 1957 .

[8]  Gerhard Widmer,et al.  Relational IBL in classical music , 2006, Machine Learning.

[9]  David P. Helmbold,et al.  Modeling, analyzing, and synthesizing expressive piano performance with graphical models , 2006, Machine Learning.

[10]  Gerhard Widmer,et al.  YQX Plays Chopin , 2009, AI Mag..

[11]  Shin-ichi Maeda,et al.  Gaussian Process Regression for Rendering Music Performance , 2008 .

[12]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[13]  Rafael Ramírez,et al.  Expressive Irish Fiddle Performance Model Informed with Bowing , 2008, ICMC.

[14]  Johan Sundberg,et al.  Musical Performance: A Synthesis-by-Rule Approach , 1983 .

[15]  Thomas L. Rhea,et al.  Evolution of the Keyboard Interface: The Bosendorfer 290 SE Recording Piano and the Moog Multiply-Touch-Sensitive Keyboards , 1990 .

[16]  R. Jackendoff,et al.  A Generative Theory of Tonal Music , 1985 .

[17]  Gerhard Widmer,et al.  The Magaloff Project: An Interim Report , 2010 .

[18]  N. Todd.  The dynamics of dynamics: A model of musical expression , 1992 .

[19]  E. Narmour.  The Analysis and Cognition of Melodic Complexity: The Implication-Realization Model , 1992 .

[20]  C. Krumhansl,et al.  Tracing the dynamic changes in perceived tonal organization in a spatial representation of musical keys. , 1982 .

[21]  J. Sundberg,et al.  Overview of the KTH rule system for musical performance. , 2006 .

[22]  Ramón López de Mántaras,et al.  An Interactive Case-Based Reasoning Approach for Generating Expressive Music , 2004, Applied Intelligence.

[23]  Eugene Narmour,et al.  The Analysis and Cognition of Basic Melodic Structures: The Implication-Realization Model , 1990 .

[24]  Gerhard Widmer,et al.  Discovering simple rules in complex data: A meta-learning algorithm and some surprising musical discoveries , 2003, Artif. Intell..

[25]  J. Sundberg,et al.  Does music performance allude to locomotion? A model of final ritardandi derived from measurements of stopping , 1999 .

[26]  D. Temperley.  Music and probability , 2006 .

[27]  Gerhard Widmer,et al.  Playing Mozart by Analogy: Learning Multi-level Timing and Dynamics Strategies , 2003 .

[28]  Kenji Suzuki,et al.  Rencon: Performance Rendering Contest for Automated Music Systems , 2008 .

[29]  Gerhard Widmer,et al.  EXPRESSIVE PERFORMANCE RENDERING: INTRODUCING PERFORMANCE CONTEXT , 2009 .

[30]  M. Grachten,et al.  Expressivity-aware tempo transformations of music performances using case based reasoning , 2006 .

[31]  Gérard Milmeister,et al.  The Rubato Composer Music Software - Component-Based Implementation of a Functorial Concept Architecture , 2009, Computational Music Science.