Expressive Performance Rendering with Probabilistic Models

Flossmann, Sebastian; Grachten, Maarten; Widmer, Gerhard

doi:10.1007/978-1-4471-4123-5_3

Cited by 11 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some of these features may be given directly by the score (such as notated pitches and durations), while others may be computed from the score in more or less elaborate ways, by some well-defined procedure (such as the cognitive features discussed in section 3.3). Features can range from low-level descriptors such as (MIDI) pitches (Friberg et al, 2006;Grindlay and Helmbold, 2006;Cancino Chacón and Grachten, 2015) and hand-crafted features, like encodings of metrical strength (Grindlay and Helmbold, 2006;Giraldo S. and Ramírez, 2016); to cognitively inspired features, like Narmour's Implication-Realization (IR) descriptors (Flossmann et al, 2013;Giraldo S.I. and Ramirez, 2016), or even features learned directly from the score using unsupervised machine learning (Grachten and Krebs, 2014;van Herwaarden et al, 2014).…”

Section: Components Of Computational Modelsmentioning

confidence: 99%

“…Several researchers use variants of Hidden Markov Models (HMMs) to describe the temporal evolution of a performance, such as Hierarchical HMMs (Grindlay and Helmbold, 2006), Dynamic Bayesian Networks (DBNs) (Widmer et al, 2009;Flossmann et al, 2011Flossmann et al, , 2013, Conditional Random Fields (CRFs) (Kim et al, 2010(Kim et al, , 2011(Kim et al, , 2013, or Switching Kalman Filters (Gu and Raphael, 2012). Furthermore, most models assume that the underlying probability distribution of the expressive parameters is Gaussian (Grindlay and Helmbold, 2006;Teramura et al, 2008;Gu and Raphael, 2012;Flossmann et al, 2013;Okumura et al, 2014). A different approach is taken by Kim et al (2013) and Moulieras and Pachet (2016), who use maximum entropy models to approximate the underlying probability distributions.…”

Section: Probabilistic Approachesmentioning

confidence: 99%

“…It defines a number of patterns of listeners' ongoing expectations regarding the continuation of a melody, and how these expectations can be realized to different degrees by the actual continuation. Methods that include features based on IR include YQX (Flossmann et al, 2013), Giraldo S.I. and Ramirez (2016)'s approach to studying expression in Jazz guitar, and Marchini et al (2014)'s approach for string quartets.…”

Section: Cognitively Inspired Featuresmentioning

confidence: 99%

See 2 more Smart Citations

Computational Models of Expressive Music Performance: A Comprehensive and Critical Review

Cancino-Chacón

Grachten

Goebl

et al. 2018

Front. Digit. Humanit.

Self Cite

View full text Add to dashboard Cite

Expressive performance is an indispensable part of music making. When playing a piece, expert performers shape various parameters (tempo, timing, dynamics, intonation, articulation, etc.) in ways that are not prescribed by the notated score, in this way producing an expressive rendition that brings out dramatic, affective, and emotional qualities that may engage and affect the listeners. Given the central importance of this skill for many kinds of music, expressive performance has become an important research topic for disciplines like musicology, music psychology, etc. This paper focuses on a specific thread of research: work on computational music performance models. Computational models are attempts at codifying hypotheses about expressive performance in terms of mathematical formulas or computer programs, so that they can be evaluated in systematic and quantitative ways. Such models can serve at least two purposes: they permit us to systematically study certain hypotheses regarding performance; and they can be used as tools to generate automated or semi-automated performances, in artistic or educational contexts. The present article presents an up-to-date overview of the state of the art in this domain. We explore recent trends in the field, such as a strong focus on data-driven (machine learning) approaches; a growing interest in interactive expressive systems, such as conductor simulators and automatic accompaniment systems; and an increased interest in exploring cognitively plausible features and models. We provide an in-depth discussion of several important design choices in such computer models, and discuss a crucial (and still largely unsolved) problem that is hindering systematic progress: the question of how to evaluate such models in scientifically and musically meaningful ways. From all this, we finally derive some research directions that should be pursued with priority, in order to advance the field and our understanding of expressive music performance.

show abstract

Section: Components Of Computational Modelsmentioning

confidence: 99%

Section: Probabilistic Approachesmentioning

confidence: 99%

Section: Cognitively Inspired Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Computational Models of Expressive Music Performance: A Comprehensive and Critical Review

Cancino-Chacón

Grachten

Goebl

et al. 2018

Front. Digit. Humanit.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The assumption is that musical patterns with expressive cues have a higher affordance for expressive responses than musical patterns without these expressive cues. A good example is the difference between deadpan piano music (e.g., a MIDI score played on a MIDI grand piano) and the same piano music onto which expressive cues are added (Flossmann et al, 2012). Listeners tend to respond more to the expressive music than to non-expressive music.…”

Section: Modification By Musical Biofeedbackmentioning

confidence: 99%

3Mo: A Model for Music-Based Biofeedback

2016

View full text Add to dashboard Cite

In the domain of sports and motor rehabilitation, it is of major importance to regulate and control physiological processes and physical motion in most optimal ways. For that purpose, real-time auditory feedback of physiological and physical information based on sound signals, often termed “sonification,” has been proven particularly useful. However, the use of music in biofeedback systems has been much less explored. In the current article, we assert that the use of music, and musical principles, can have a major added value, on top of mere sound signals, to the benefit of psychological and physical optimization of sports and motor rehabilitation tasks. In this article, we present the 3Mo model to describe three main functions of music that contribute to these benefits. These functions relate the power of music to Motivate, and to Monitor and Modify physiological and physical processes. The model brings together concepts and theories related to human sensorimotor interaction with music, and specifies the underlying psychological and physiological principles. This 3Mo model is intended to provide a conceptual framework that guides future research on musical biofeedback systems in the domain of sports and motor rehabilitation.

show abstract

“…We refer the interested reader to either [1] (the first one and still relevant), [2] (our own study) or [3] (the most recent). Attempts to use that knowledge to allow computers to expressively perform music also exists [30,31].…”

Section: Music Performancementioning

confidence: 99%