Getting Closer to the Essence of Music

  title={Getting Closer to the Essence of Music},
  author={G. Widmer},
  journal={ACM Transactions on Intelligent Systems and Technology (TIST)},
  pages={1 - 13}
  • G. Widmer
  • Published 2017
  • Computer Science
  • ACM Transactions on Intelligent Systems and Technology (TIST)
This text offers a personal and very subjective view on the current situation of Music Information Research (MIR). Motivated by the desire to build systems with a somewhat deeper understanding of music than the ones we currently have, I try to sketch a number of challenges for the next decade of MIR research, grouped around six simple truths about music that are probably generally agreed on but often ignored in everyday research. 
The Impact of the Complexity of Harmony on the Acceptability of Music
All the measures of complexity proposed are consistent and are together with the musical style important features in explaining the musical acceptability, and the regularity of the harmonic progression is in both cases the most important predictor. Expand
This time with feeling: learning expressive musical performance
An LSTM-based recurrent network model is shown that subjectively performs quite well on this task and is considered to be valuable to work in the space of direct performance generation: jointly predicting the notes and also their expressive timing and dynamics. Expand
On the Characterization of Expressive Performance in Classical Music: First Results of the Con Espressione Game
A piece of music can be expressively performed, or interpreted, in a variety of ways. With the help of an online questionnaire, the Con Espressione Game, we collected some 1,500 descriptions ofExpand
Automatic estimation of harmonic tension by distributed representation of chords
The buildup and release of a sense of tension is one of the most essential aspects of the process of listening to music. A veridical computational model of perceived musical tension would be anExpand
Towards Explainable Music Emotion Recognition: The Route via Mid-level Features
A VGG-style deep neural network that learns to predict emotional characteristics of a musical piece together with (and based on) human-interpretable, mid-level perceptual features that is justified by the gain in explainability of the predictions. Expand
Computational Models of Expressive Music Performance: A Comprehensive and Critical Review
An up-to-date overview of the state of the art in computational music performance models is presented, including recent trends in the field, such as a strong focus on data-driven (machine learning); a growing interest in interactive expressive systems; and an increased interest in exploring cognitively plausible features and models. Expand
Conceptual blending of high-level features and data-driven salience computation in melodic generation
A novel approach to generating new material that allows blending high-level features by combining low-level structures, based on statistically computed salience values for each high- level feature extracted from data is proposed. Expand
Taming wild horses with Essentia Music Extractor
This work overviews the work done on automatic music audio description using the Essentia Music Extractor, and identifies how it can be improved in following versions to be in line with the essential goals of Music Information Retrieval of building final usable systems. Expand
A Joyful Ode to Automatic Orchestration
  • F. Pachet
  • Computer Science
  • ACM Trans. Intell. Syst. Technol.
  • 2017
This article reports on a specific experiment in holistic music generation: the reorchestration of Beethoven’s Ode to Joy, the European anthem, in seven styles, produced with algorithms developed in the Flow Machines project and within a short time frame. Expand
Automatically Generating Novel and Epic Music Tracks
Computational Creativity is an applied field of study focused on algorithms that allow a better understanding of the creativity processes or simply perform some task usually considered creative.Expand


Computational Models of Expressive Music Performance: The State of the Art
This contribution gives an overview of the state of the art in the field of computational modeling of expressive music performance by reviewing a number of quantitative models of various aspects of expressive performance. Expand
Memory-Based Models of Melodic Analysis: Challenging the Gestalt Principles
  • R. Bod
  • Computer Science, Physics
  • 2001
It is argued that music perception may be much more memory-based than previously assumed, and there are grouping phenomena that challenge the commonly accepted Gestalt principles of proximity, similarity and parallelism. Expand
The neglected user in music information retrieval research
This article investigates and discusses literature on the topic of user-centric music retrieval and reflects on why the breakthrough in this field has not been achieved yet, and presents ideas on aspects crucial to consider when elaborating user-aware music retrieval systems. Expand
A Multicultural Approach in Music Information Research
The motivation behind a large and ambitious project funded by the European Research Council entitled "CompMusic: Computational Models for the discovery of the world's music" is presented, the challenges that the project wants to work on, and the proposed approaches to tackle these challenges. Expand
This paper surveys the state of the art in automatic emotion recognition in music. Music is oftentimes referred to as a “language of emotion” [1], and it is natural for us to categorize music inExpand
Auditory Expectation: The Information Dynamics of Music Perception and Cognition
A range of evidence is summarized for this approach, from psychology, neuroscience, musicology, linguistics, and creativity studies, and it is argued that simulating expectation is an important part of understanding a broad range of human faculties, in music and beyond. Expand
State of the Art Report: Audio-Based Music Structure Analysis
This paper gives an overview of state-of-theart methods for computational music structure analysis, where the general goal is to divide an audio recording into temporal segments corresponding to musical parts and to group these segments into musically meaningful categories. Expand
What does music express? Basic emotions and beyond
  • P. Juslin
  • Psychology, Medicine
  • Front. Psychol.
  • 2013
It is argued that the content of emotional content in music is mainly constrained by the type of coding involved, and that distinct types of content are related to different types of coding. Expand
On the non-existence of music: Why music theory is a figment of the imagination
We argue for an approach to the theory of music which starts from the position that music is primarily a construct of human minds (and secondarily a social construct) and contrast it with theExpand
The Continuator: Musical Interaction With Style
The Continuator is a system that bridges the gap between two classes of traditionally incompatible musical systems, based on a Markov model of musical styles augmented to account for musical issues such as management of rhythm, beat, harmony, and imprecision. Expand