Gerhard Widmer

IJCAI Conference 2024 Conference Paper

Perception-Inspired Graph Convolution for Music Understanding Tasks

• Emmanouil Karystinaios
• Francesco Foscarin
• Gerhard Widmer

We propose a new graph convolutional block, called MusGConv, specifically designed for the efficient processing of musical score data and motivated by general perceptual principles. It focuses on two fundamental dimensions of music, pitch and rhythm, and considers both relative and absolute representations of these components. We evaluate our approach on four different musical understanding problems: monophonic voice separation, harmonic analysis, cadence detection, and composer identification which, in abstract terms, translate to different graph learning problems, namely, node classification, link prediction, and graph classification. Our experiments demonstrate that MusGConv improves the performance on three of the aforementioned tasks while being conceptually very simple and efficient. We interpret this as evidence that it is beneficial to include perception-informed processing of fundamental musical concepts when developing graph network applications on musical score data. All code and models are released on https: //github. com/manoskary/musgconv.

IJCAI Conference 2023 Conference Paper

Discrete Diffusion Probabilistic Models for Symbolic Music Generation

• Matthias Plasser
• Silvan Peter
• Gerhard Widmer

Denoising Diffusion Probabilistic Models (DDPMs) have made great strides in generating high-quality samples in both discrete and continuous domains. However, Discrete DDPMs (D3PMs) have yet to be applied to the domain of Symbolic Music. This work presents the direct generation of Polyphonic Symbolic Music using D3PMs. Our model exhibits state-of-the-art sample quality, according to current quantitative evaluation metrics, and allows for flexible infilling at the note level. We further show, that our models are accessible to post-hoc classifier guidance, widening the scope of possible applications. However, we also cast a critical view on quantitative evaluation of music sample quality via statistical metrics, and present a simple algorithm that can confound our metrics with completely spurious, non-musical samples.

IJCAI Conference 2023 Conference Paper

Musical Voice Separation as Link Prediction: Modeling a Musical Perception Task as a Multi-Trajectory Tracking Problem

• Emmanouil Karystinaios
• Francesco Foscarin
• Gerhard Widmer

This paper targets the perceptual task of separating the different interacting voices, i. e. , monophonic melodic streams, in a polyphonic musical piece. We target symbolic music, where notes are explicitly encoded, and model this task as a Multi-Trajectory Tracking (MTT) problem from discrete observations, i. e. , notes in a pitch-time space. Our approach builds a graph from a musical piece, by creating one node for every note, and separates the melodic trajectories by predicting a link between two notes if they are consecutive in the same voice/stream. This kind of local, greedy prediction is made possible by node embeddings created by a heterogeneous graph neural network that can capture inter- and intra-trajectory information. Furthermore, we propose a new regularization loss that encourages the output to respect the MTT premise of at most one incoming and one outgoing link for every node, favoring monophonic (voice) trajectories; this loss function might also be useful in other general MTT scenarios. Our approach does not use domain-specific heuristics, is scalable to longer sequences and a higher number of voices, and can handle complex cases such as voice inversions and overlaps. We reach new state-of-the-art results for the voice separation task on classical music of different styles. All code, data, and pretrained models are available on https: //github. com/manoskary/vocsep_ijcai2023

IJCAI Conference 2023 Conference Paper

The ACCompanion: Combining Reactivity, Robustness, and Musical Expressivity in an Automatic Piano Accompanist

• Carlos Cancino-Chacón
• Silvan Peter
• Patricia Hu
• Emmanouil Karystinaios
• Florian Henkel
• Francesco Foscarin
• Gerhard Widmer

This paper introduces the ACCompanion, an expressive accompaniment system. Similarly to a musician who accompanies a soloist playing a given musical piece, our system can produce a human-like rendition of the accompaniment part that follows the soloist's choices in terms of tempo, dynamics, and articulation. The ACCompanion works in the symbolic domain, i. e. , it needs a musical instrument capable of producing and playing MIDI data, with explicitly encoded onset, offset, and pitch for each played note. We describe the components that go into such a system, from real-time score following and prediction to expressive performance generation and online adaptation to the expressive choices of the human player. Based on our experience with repeated live demonstrations in front of various audiences, we offer an analysis of the challenges of combining these components into a system that is highly reactive and precise, while still a reliable musical partner, robust to possible performance errors and responsive to expressive variations.

TIST Journal 2016 Journal Article

Getting Closer to the Essence of Music

• Gerhard Widmer

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.

IJCAI Conference 2015 Conference Paper

Artificial Intelligence in the Concertgebouw

• Andreas Arzt
• Harald Frostel
• Thassilo Gadermaier
• Martin Gasser
• Maarten Grachten
• Gerhard Widmer

In this paper we present a real-world application (the first of its kind) of machine listening in the context of a live concert in a world-famous concert hall – the Concertgebouw in Amsterdam. A real-time music tracking algorithm listens to the Royal Concertgebouw Orchestra performing Richard Strauss’ Alpensinfonie and follows the progress in the sheet music, i. e. , continuously tracks the most likely position of the live music in the printed score. This information, in turn, is used to enrich the concert experience for members of the audience by streaming synchronised visual content (the sheet music, explanatory text and videos) onto tablet computers in the concert hall. The main focus of this paper is on the challenges involved in tracking live orchestral music, i. e. , how to deal with heavily polyphonic music, how to prepare the data needed, and how to achieve the necessary robustness and precision.

ECAI Conference 2014 Conference Paper

The Piano Music Companion

• Andreas Arzt
• Sebastian Böck
• Sebastian Flossmann
• Harald Frostel
• Martin Gasser
• Cynthia C. S. Liem
• Gerhard Widmer

We present a system that we call 'The Piano Music Companion' and that is able to follow and understand (at least to some extent) a live piano performance. Within a few seconds this system can identify the piece that is being played, and the position within the piece. It then tracks the progress of the performer over time via a robust score following algorithm. The companion is useful in multiple ways, e. g. , it can be used for piece identification, music visualisation, during piano rehearsal and for automatic page turning.

JMLR Journal 2012 Journal Article

Local and Global Scaling Reduce Hubs in Space

• Dominik Schnitzer
• Arthur Flexer
• Markus Schedl
• Gerhard Widmer

'Hubness' has recently been identified as a general problem of high dimensional data spaces, manifesting itself in the emergence of objects, so-called hubs, which tend to be among the k nearest neighbors of a large number of data items. As a consequence many nearest neighbor relations in the distance space are asymmetric, that is, object y is amongst the nearest neighbors of x but not vice versa. The work presented here discusses two classes of methods that try to symmetrize nearest neighbor relations and investigates to what extent they can mitigate the negative effects of hubs. We evaluate local distance scaling and propose a global variant which has the advantage of being easy to approximate for large data sets and of having a probabilistic interpretation. Both local and global approaches are shown to be effective especially for high-dimensional data sets, which are affected by high hubness. Both methods lead to a strong decrease of hubness in these data sets, while at the same time improving properties like classification accuracy. We evaluate the methods on a large number of public machine learning data sets and synthetic data. Finally we present a real-world application where we are able to achieve significantly higher retrieval quality. [abs] [ pdf ][ bib ] &copy JMLR 2012. ( edit, beta )

ECAI Conference 2012 Conference Paper

Towards a Complete Classical Music Companion

• Andreas Arzt
• Gerhard Widmer
• Sebastian Böck
• Reinhard Sonnleitner
• Harald Frostel

We present a system that listens to music on-line and almost instantly identifies the piece the performers are playing and the exact position in the musical score. This is achieved via a combination of a state-of-the-art audio-to-note transcription algorithm and a novel symbolic fingerprinting method. The speed and precision of the system are evaluated in systematic experiments with a large corpus of classical music recordings. The results indicate extremely fast and accurate recognition performance - a level of performance, in fact, that even human experts in classical music will find hard to match.

ECAI Conference 2008 Conference Paper

Automatic Page Turning for Musicians via Real-Time Machine Listening

• Andreas Arzt
• Gerhard Widmer
• Simon Dixon

We present a system that automatically turns the pages of the music score for musicians during a performance. It is based on a new algorithm for following an incoming audio stream in real time and aligning it to a music score (in the form of a synthesised audio file). Precision and robustness of the algorithm are quantified in systematic experiments, and a demonstration using an actual page turning machine built by an Austrian company is described.

IJCAI Conference 2007 Conference Paper

• S
• oslash; ren Tjagvad Madsen
• Gerhard Widmer

This paper presents first steps towards a simple, robust computational model of automatic melody identification. Based on results from music psychology that indicate a relationship between melodic complexity and a listener's attention, we postulate a relationship between musical complexity and the probability of a musical line to be perceived as the melody. We introduce a simple measure of melodic complexity, present an algorithm for predicting the most likely melody note at any point in a piece, and show experimentally that this simple approach works surprisingly well in rather complex music.

AIJ Journal 2005 Journal Article

Automatic identification of music performers with learning ensembles

• Efstathios Stamatatos
• Gerhard Widmer

This article addresses the problem of identifying the most likely music performer, given a set of performances of the same piece by a number of skilled candidate pianists. We propose a set of very simple features for representing stylistic characteristics of a music performer, introducing ‘norm-based’ features that relate to a kind of ‘average’ performance. A database of piano performances of 22 pianists playing two pieces by Frédéric Chopin is used in the presented experiments. Due to the limitations of the training set size and the characteristics of the input features we propose an ensemble of simple classifiers derived by both subsampling the training set and subsampling the input features. Experiments show that the proposed features are able to quantify the differences between music performers. The proposed ensemble can efficiently cope with multi-class music performer recognition under inter-piece conditions, a difficult musical task, displaying a level of accuracy unlikely to be matched by human listeners (under similar conditions).

ECAI Conference 2004 Conference Paper

Automatic Recognition of Famous Artists by Machine

• Gerhard Widmer
• Patrick Zanon

AIJ Journal 2003 Journal Article

Discovering simple rules in complex data: A meta-learning algorithm and some surprising musical discoveries

• Gerhard Widmer

This article presents a new rule discovery algorithm named PLCG that can find simple, robust partial rule models (sets of classification rules) in complex data where it is difficult or impossible to find models that completely account for all the phenomena of interest. Technically speaking, PLCG is an ensemble learning method that learns multiple models via some standard rule learning algorithm, and then combines these into one final rule set via clustering, generalization, and heuristic rule selection. The algorithm was developed in the context of an interdisciplinary research project that aims at discovering fundamental principles of expressive music performance from large amounts of complex real-world data (specifically, measurements of actual performances by concert pianists). It will be shown that PLCG succeeds in finding some surprisingly simple and robust performance principles, some of which represent truly novel and musically meaningful discoveries. A set of more systematic experiments shows that PLCG usually discovers significantly simpler theories than more direct approaches to rule learning (including the state-of-the-art learning algorithm Ripper), while striking a compromise between coverage and precision. The experiments also show how easy it is to use PLCG as a meta-learning strategy to explore different parts of the space of rule models.

ECAI Conference 2002 Conference Paper

Music Performer Recognition Using an Ensemble of Simple Classifiers

• Efstathios Stamatatos
• Gerhard Widmer

ICML Conference 2002 Conference Paper

Transformation-Based Regression

• Björn Bringmann
• Stefan Kramer 0001
• Friedrich Neubarth
• Hannes Pirker
• Gerhard Widmer

ICML Conference 1996 Conference Paper

Recognition and Exploitation of Contextual CLues via Incremental Meta-Learning

• Gerhard Widmer

ECAI Conference 1996 Conference Paper

What Is It That Makes It a Horowitz? Empirical Musicology via Machine Learning

• Gerhard Widmer

ECAI Conference 1994 Conference Paper

Combining Robustness and Flexibility in Learning Drifting Concepts

• Gerhard Widmer

ICML Conference 1994 Conference Paper

Incremental Reduced Error Pruning

• Johannes Fürnkranz
• Gerhard Widmer

AAAI Conference 1994 Conference Paper

The Synergy of Music Theory and AI: Learning Multi-Level Expressive Interpretation

• Gerhard Widmer

The paper presents interdisciplinary research in the intersection of AI (machine learning) and Art (music). We describe an implemented system that learns expressive interpretation of music pieces from performances by human musicians. The problem, shown to be very difficult in the introduction, is solved by combining insights from music theory with a new machine learning algorithm. Theoretically founded knowledge about music perception is used to transform the original learning problem to a more abstract level where relevant regularities become apparent. Experiments with performances of Chopin waltzes are presented; the results indicate musical understanding and the ability to learn a complex task from very little training data. As the system’ s domain knowledge is based on two established theories of tonal music, the results also have interesting implications for music theory.

AIIM Journal 1993 Journal Article

Automatic knowledge base refinement: Learning from examples and deep knowledge in rheumatology

• Gerhard Widmer
• Werner Horn
• Bernhard Nagele

MESICAR is a second generation expert system which contains very general descriptions of rheumatological disorders in the primary medical care field. With the help of a detailed hierarchical description of the human anatomy the system is able to support diagnostic decisions. The paper describes how machine learning techniques are used to automatically construct more specific disease descriptions for common, frequently occurring cases. The system MESICAR-LEARN implements a learning method which integrates analytical and empirical learning techniques. Cases diagnosed by MESICAR form the training examples, and MESICAR's knowledge base is used as domain theory. The leamed concepts are integrated into a hierarchy of disease descriptions. They support efficient and fast reasoning on common cases in addition to the general diagnostic support afforded by MESICAR's deep knowledge.

ECAI Conference 1992 Conference Paper

Learning Flexible Concepts from Streams of Examples: FLORA 2

• Gerhard Widmer
• Miroslav Kubat