Gerhard Widmer
Biographic Data
| ID | 3820542 |
|---|---|
| NAME | Gerhard Widmer |
| GIVEN NAMES | Gerhard |
| FAMILY NAME | Widmer |
| SIGNATURE | WIDMER G |
| AFFILIATIONS | Austrian Research Institute for Artificial Intelligence |
| ORCID | 0000-0003-3531-1282 |
| VERIFIED | No |
| TOTAL WORKS | 11 |
| TOTAL CITATIONS | 27 |
| AUTHOR COUNT | 11 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 1992 |
| LATEST PUBLICATION YEAR | 2012 |
| H-INDEX | 3 |
Linear Basis Models for Prediction and Analysis of Musical Expression
The quest for understanding how pianists interpret notated music to turn it into a lively musical experience, has led to numerous models of musical expression. Several models exist that explain expressive variations over the course of a performance, for example in terms of phrase structure, or musical accent. Often however expressive markings are written explicitly in the score to guide performers. We present a modelling framework for musical exp…
The Magaloff Project
One of the main difficulties in studying expression in musical performance is the acquisition of data. While audio recordings abound, automatically extracting precise information related to timing, dynamics, and articulation is still not possible at the level of precision required for large-scale music performance studies. In 1989, the Russian pianist Nikita Magaloff performed essentially the entire works for solo piano by Frédéric Chopin on a Bö…
Phase-plane Representation and Visualization of Gestural Structure in Expressive Timing
For the past few decades there has been considerable scientific interest in expression in music performance (Gabrielsson, Citation2003). A particularly relevant aspect of music performance is expressive timing, that is, the intentional fluctuations of tempo during a performance. Accordingly, expressive timing has been one of the major topics in music performance research. As an expressive parameter, timing is used to clarify the musical structure…
Sound and Music Computing
This contribution attempts to give an overview of current research trends and open research problems in the rich field of Sound and Music Computing (SMC). To that end, the field is roughly divided into three large areas related to Sound, Music, and Interaction, respectively, and within each of these, major research trends are briefly described. In addition, for each sub-field a small number of open research (or research strategy) issues are ident…
Studying a creative act with computers
The purpose of this article is to demonstrate how advanced computer methods may be able to provide new insights into a complex creative activity such as music performance. The context is an inter-disciplinary research project in which Artificial Intelligence (AI) methods are used to analyse patterns in performances by human artists. In asking how the computer can take us closer to an understanding of creativity in music performance, we identify t…
Computational Models of Expressive Music Performance
This contribution gives an overview of the state of the art in the field of computational modeling of expressive music performance. The notion of predictive computational model is briefly discussed, and a number of quantitative models of various aspects of expressive performance are briefly reviewed. Four selected computational models are reviewed in some detail. Their basic principles and assumptions are explained and, wherever possible, empiric…
Playing Mozart by Analogy
The paper describes basic research in the area of machine learning and musical expression. A first step towards automatic induction of multi-level models of expressive performance (currently only tempo and dynamics) from real performances by skilled pianists is presented. The goal is to learn to apply sensible tempo and dynamics `shapes' at various levels of the hierarchical musical phrase structure. We propose a general method for decomposing gi…
Machine Discoveries
The paper presents a new approach to discovering general rules of expressive music performance from real performance data via inductive machine learning. A new learning algorithm is briey presented, and then an experiment with a very large data set (performances of 13 Mozart piano sonatas) is described. The new learning algorithm succeeds in discovering some extremely simple and general principles of musical performance (at the level of individua…
Automated Motivic Analysis via Melodic Clustering
In this paper a computational model will be presented that attempts to organise melodic segments into ‘significant’ musical categories (e.g., motives). Given a segmentation of a melodic surface, the proposed algorithm constructs an appropriate representation for each segment in terms of a number of attributes (these reflect melodic and rhythmic aspects of the segment at the surface and at various abstract levels) and then a clustering algorithm (…
Learning expressive performance
This article describes recent work in the area of music and artificial intelligence (AI) that aims at developing working models of musical learning. An implemented AI program is presented that learns general rules of expressive performance (for dynamics and rubato) from examples of human performances. The method improves upon previous research by the author (Widmer 1995a), where expression rules were learned at the level of individual notes with …
Art/ificial Intelligence
Computational Models of Expressive Music Performance
This contribution gives an overview of the state of the art in the field of computational modeling of expressive music performance. The notion of predictive computational model is briefly discussed, and a number of quantitative models of various aspects of expressive performance are briefly reviewed. Four selected computational models are reviewed in some detail. Their basic principles and assumptions are explained and, wherever possible, empiric…
Machine Discoveries
The paper presents a new approach to discovering general rules of expressive music performance from real performance data via inductive machine learning. A new learning algorithm is briey presented, and then an experiment with a very large data set (performances of 13 Mozart piano sonatas) is described. The new learning algorithm succeeds in discovering some extremely simple and general principles of musical performance (at the level of individua…
Linear Basis Models for Prediction and Analysis of Musical Expression
The quest for understanding how pianists interpret notated music to turn it into a lively musical experience, has led to numerous models of musical expression. Several models exist that explain expressive variations over the course of a performance, for example in terms of phrase structure, or musical accent. Often however expressive markings are written explicitly in the score to guide performers. We present a modelling framework for musical exp…
The Magaloff Project
One of the main difficulties in studying expression in musical performance is the acquisition of data. While audio recordings abound, automatically extracting precise information related to timing, dynamics, and articulation is still not possible at the level of precision required for large-scale music performance studies. In 1989, the Russian pianist Nikita Magaloff performed essentially the entire works for solo piano by Frédéric Chopin on a Bö…
Sound and Music Computing
This contribution attempts to give an overview of current research trends and open research problems in the rich field of Sound and Music Computing (SMC). To that end, the field is roughly divided into three large areas related to Sound, Music, and Interaction, respectively, and within each of these, major research trends are briefly described. In addition, for each sub-field a small number of open research (or research strategy) issues are ident…
Playing Mozart by Analogy
The paper describes basic research in the area of machine learning and musical expression. A first step towards automatic induction of multi-level models of expressive performance (currently only tempo and dynamics) from real performances by skilled pianists is presented. The goal is to learn to apply sensible tempo and dynamics `shapes' at various levels of the hierarchical musical phrase structure. We propose a general method for decomposing gi…
Phase-plane Representation and Visualization of Gestural Structure in Expressive Timing
For the past few decades there has been considerable scientific interest in expression in music performance (Gabrielsson, Citation2003). A particularly relevant aspect of music performance is expressive timing, that is, the intentional fluctuations of tempo during a performance. Accordingly, expressive timing has been one of the major topics in music performance research. As an expressive parameter, timing is used to clarify the musical structure…
Automated Motivic Analysis via Melodic Clustering
In this paper a computational model will be presented that attempts to organise melodic segments into ‘significant’ musical categories (e.g., motives). Given a segmentation of a melodic surface, the proposed algorithm constructs an appropriate representation for each segment in terms of a number of attributes (these reflect melodic and rhythmic aspects of the segment at the surface and at various abstract levels) and then a clustering algorithm (…
Learning expressive performance
This article describes recent work in the area of music and artificial intelligence (AI) that aims at developing working models of musical learning. An implemented AI program is presented that learns general rules of expressive performance (for dynamics and rubato) from examples of human performances. The method improves upon previous research by the author (Widmer 1995a), where expression rules were learned at the level of individual notes with …
Art/ificial Intelligence
Learning expressive performance
This article describes recent work in the area of music and artificial intelligence (AI) that aims at developing working models of musical learning. An implemented AI program is presented that learns general rules of expressive performance (for dynamics and rubato) from examples of human performances. The method improves upon previous research by the author (Widmer 1995a), where expression rules were learned at the level of individual notes with …
Automated Motivic Analysis via Melodic Clustering
In this paper a computational model will be presented that attempts to organise melodic segments into ‘significant’ musical categories (e.g., motives). Given a segmentation of a melodic surface, the proposed algorithm constructs an appropriate representation for each segment in terms of a number of attributes (these reflect melodic and rhythmic aspects of the segment at the surface and at various abstract levels) and then a clustering algorithm (…
Machine Discoveries
The paper presents a new approach to discovering general rules of expressive music performance from real performance data via inductive machine learning. A new learning algorithm is briey presented, and then an experiment with a very large data set (performances of 13 Mozart piano sonatas) is described. The new learning algorithm succeeds in discovering some extremely simple and general principles of musical performance (at the level of individua…
Playing Mozart by Analogy
The paper describes basic research in the area of machine learning and musical expression. A first step towards automatic induction of multi-level models of expressive performance (currently only tempo and dynamics) from real performances by skilled pianists is presented. The goal is to learn to apply sensible tempo and dynamics `shapes' at various levels of the hierarchical musical phrase structure. We propose a general method for decomposing gi…
Computational Models of Expressive Music Performance
This contribution gives an overview of the state of the art in the field of computational modeling of expressive music performance. The notion of predictive computational model is briefly discussed, and a number of quantitative models of various aspects of expressive performance are briefly reviewed. Four selected computational models are reviewed in some detail. Their basic principles and assumptions are explained and, wherever possible, empiric…
Studying a creative act with computers
The purpose of this article is to demonstrate how advanced computer methods may be able to provide new insights into a complex creative activity such as music performance. The context is an inter-disciplinary research project in which Artificial Intelligence (AI) methods are used to analyse patterns in performances by human artists. In asking how the computer can take us closer to an understanding of creativity in music performance, we identify t…
Sound and Music Computing
This contribution attempts to give an overview of current research trends and open research problems in the rich field of Sound and Music Computing (SMC). To that end, the field is roughly divided into three large areas related to Sound, Music, and Interaction, respectively, and within each of these, major research trends are briefly described. In addition, for each sub-field a small number of open research (or research strategy) issues are ident…
Phase-plane Representation and Visualization of Gestural Structure in Expressive Timing
For the past few decades there has been considerable scientific interest in expression in music performance (Gabrielsson, Citation2003). A particularly relevant aspect of music performance is expressive timing, that is, the intentional fluctuations of tempo during a performance. Accordingly, expressive timing has been one of the major topics in music performance research. As an expressive parameter, timing is used to clarify the musical structure…
The Magaloff Project
One of the main difficulties in studying expression in musical performance is the acquisition of data. While audio recordings abound, automatically extracting precise information related to timing, dynamics, and articulation is still not possible at the level of precision required for large-scale music performance studies. In 1989, the Russian pianist Nikita Magaloff performed essentially the entire works for solo piano by Frédéric Chopin on a Bö…
Linear Basis Models for Prediction and Analysis of Musical Expression
The quest for understanding how pianists interpret notated music to turn it into a lively musical experience, has led to numerous models of musical expression. Several models exist that explain expressive variations over the course of a performance, for example in terms of phrase structure, or musical accent. Often however expressive markings are written explicitly in the score to guide performers. We present a modelling framework for musical exp…
Computer Science (11 works) · Music Technology and Sound Studies (10 works) · Artificial Intelligence (9 works) · Music and Audio Processing (9 works) · Neuroscience and Music Perception (8 works) · Mathematics (5 works) · Musical (5 works) · Piano (4 works) · Psychology (4 works) · Visual arts (4 works)