Getting at the Heart of Things: Towards Expressivity-aware Computer Systems in Music

Publications

Conference proceedings (53)

Investigating Label Noise Sensitivity of Convolutional Neural Networks for Fine-grained Audio Signal Labelling

Author(s): Rainer Kelz, Gerhard Widmer
Published in: Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018), 2018

The Importance of Song Context and Song Order in Automated Music Playlist Generation

Author(s): Andreu Vall, Massimo Quadrana, Markus Schedl, Gerhard Widmer
Published in: Proceedings of the 15th International Conference on Music Perception and Cognition (ICMPC 2018) & 10th Triennial Conference of the European Society for the Cognitive Sciences of Music (ESCOM 2018), 2018

Psychological Constraints on String-based Methods for Pattern Discovery in Polyphonic Corpora

Author(s): David Sears, Gerhard Widmer
Published in: Proceedings of the 15th International Conference on Music Perception and Cognition (ICMPC 2018) & 10th Triennial Conference of the European Society for the Cognitive Sciences of Music (ESCOM 2018), 2018

A Hybrid Approach to Music Playlist Continuation Based on Playlist-Song Membership

Author(s): Andreu Vall, Matthias Dorfer, Markus Schedl, Gerhard Widmer
Published in: Proceedings of the Symposium on Applied Computing (SAC 2018), 2018

A Large-Scale Study of Language Models for Chord Prediction

Author(s): Filip Korzeniowski, David Sears, Gerhard Widmer
Published in: Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018), 2018

A Computational Study of the Role of Tonal Tension in Expressive Piano Performance

Author(s): Carlos Eduardo Cancino-Chacon, Maarten Grachten
Published in: Proceedings of the 15th International Conference on Music Perception and Cognition (ICMPC 2018) & 10th Triennial Conference of the European Society for the Cognitive Sciences of Music (ESCOM 2018), 2018

Modeling Majorness as a Perceptual Property of Music

Author(s): Anna Aljanaki, Gerhard Widmer
Published in: Proceedings of the 15th International Conference on Music Perception and Cognition (ICMPC 2018) & 10th Triennial Conference of the European Society for the Cognitive Sciences of Music (ESCOM 2018), 2018

A Predictive Model for Music Based on Learned Relative Pitch Representations

Author(s): Stefan Lattner, Maarten Grachten, Gerhard Widmer
Published in: Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR 2018), 2018

Evaluating Language Models of Tonal Harmony

Author(s): David Sears, Filip Korzeniowski, Gerhard Widmer
Published in: Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR 2018), 2018

A Data-driven Approach to Mid-level Perceptual Feature Modeling

Author(s): Anna Aljanaki, Mohammad Soleymani
Published in: Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR 2018), 2018

Learning Transposition-Invariant Interval Features from Symbolic Music and Audio

Author(s): Stefan Lattner, Maarten Grachten, Gerhard Widmer
Published in: Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR 2018), 2018

Towards Multi-Instrument Drum Transcription

Author(s): Richard Vogl, Gerhard Widmer, Peter Knees
Published in: Proceedings of the 2018 International Conference on Digital Audio Effects (DAFx 2018), 2018

Genre-agnostic Key Classification with Convolutional Neural Networks

Author(s): Filip Korzeniowski, Gerhard Widmer
Published in: Proceedings of the 19th International Society for Music Information Retrieval Conference (ISMIR 2018), 2018

Learning to Listen, Read, and Follow: Score Following as a Reinforcement Learning Game

Author(s): Matthias Dorfer, Florian Henkel, Gerhard Widmer
Published in: Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR 2018), 2018

Audio-to-Score Alignment using Transposition-invariant Features

Author(s): Andreas Arzt, Stefan Lattner
Published in: Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR 2018), 2018

Automatic Chord Recognition with Higher-Order Harmonic Language Modelling

Author(s): Filip Korzeniowski, Gerhard Widmer
Published in: Proceedings of the 26th European Signal Processing Conference (EUSIPCO 2018), 2018

Improved Chord Recognition by Combining Duration and Harmonic Language Models

Author(s): Filip Korzeniowski, Gerhard Widmer
Published in: Proceedings of the 19th International Society for Music Information Retrieval Conference (ISMIR 2018), 2018

Machine Learning Approaches to Hybrid Music Recommender Systems

Author(s): Andreu Vall, Gerhard Widmer
Published in: Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD 2018), 2018

Attention as a Perspective for Learning Tempo-invariant Audio Queries

Author(s): Matthias Dorfer, Jan Hajic, Gerhard Widmer
Published in: Proceedings of the Joint ICML, IJCAI/ECAI, AAMAS Workshop on Machine Learning for Music, 2018

Feature Learning for Chord Recognition: The Deep Chroma Extractor

Author(s): Filip Korzeniowski, Gerhard Widmer
Published in: Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR 2016), 2016

Live Score Following on Sheet Music Images

Author(s): Matthias Dorfer, Andreas Arzt, Sebastian Böck, Amaury Durand, Gerhard Widmer
Published in: 17th International Society for Music Information Retrieval Conference (ISMIR 2016), Late Breaking/Demo Papers, 2016

Towards Score Following in Sheet Music Images

Author(s): Matthias Dorfer, Andreas Arzt, Gerhard Widmer
Published in: Proceedings of the 17th International Society for Music Information Retrieval Conference (2016), 2016

Towards End-to-End Audio-Sheet-Music Retrieval

Author(s): Matthias Dorfer, Andreas Arzt, Gerhard Widmer
Published in: NIPS 2016 End-to-end Learning for Speech and Audio Processing Workshop, 2016

On the Potential of Simple Framewise Approaches to Piano Transcription

Author(s): Rainer Kelz, Matthias Dorfer, Filip Korzeniowski, Sebastian Boeck, Andreas Arzt, Gerhard Widmer
Published in: Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR 2016), 2016

A fully convolutional deep auditory model for musical chord recognition

Author(s): Filip Korzeniowski, Gerhard Widmer
Published in: 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP), 2016, Page(s) 1-6
DOI: 10.1109/MLSP.2016.7738895

Multitask Learning for Polyphonic Piano Transcription, a Case Study

Author(s): Rainer Kelz, Sebastian Böck, Gerhard Widmer
Published in: Proceedings of the First International Workshop on Multilayer Music Representation and Processing (MMRP19), 2019

Deep Polyphonic ADSR Piano Note Transcription

Author(s): Rainer Kelz, Sebastian Böck, Gerhard Widmer
Published in: Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2019), 2019

A Sequencer with Decoupled Track Timing. (Demonstration Paper)

Author(s): Silvan David Peter, Gerhard Widmer
Published in: Proceedings of the 16th Sound & Music Computing Conference (SMC 2019), 2019

Two-level Explanations in Music Emotion Recognition

Author(s): Verena Haunschmid, Shreyan Chowdhury, Gerhard Widmer
Published in: ICML 2019 Workshop on Machine Learning for Music Discovery, 36th International Conference on Machine Learning (ICML 2019), 2019

User Curated Shaping of Expressive Performances.

Author(s): Zhengshan Shi, Carlos Eduardo Cancino-Chacón, Gerhard Widmer
Published in: ICML 2019 Workshop on Machine Learning for Music Discovery, 36th International Conference on Machine Learning (ICML 2019), 2019

Towards Interpretable Polyphonic Transcription with Invertible Neural Networks

Author(s): Rainer Kelz, Gerhard Widmer
Published in: Proceedings of the 20th International Society for Music Information Retrieval Conference (ISMIR 2019), 2019

Towards Explainable Music Emotion Recognition: The Route via Mid-level Features.

Author(s): Shreyan Chowdhury, Verena Haunschmid, Gerhard Widmer
Published in: Proceedings of the 20th International Society for Music Information Retrieval Conference (ISMIR 2019), 2019

A Study of Annotation and Alignment Accuracy for Performance Comparison in Complex Orchestral Music

Author(s): Thassilo Gadermaier, Gerhard Widmer
Published in: Proceedings of the 20th International Society for Music Information Retrieval Conference (ISMIR 2019), 2019

Learning Soft-Attention Models for Tempo-invariant Audio-Sheet Music Retrieval

Author(s): Stefan Balke, Matthias Dorfer, Luis Carvalho, Andreas Arzt, Gerhard Widmer
Published in: Proceedings of the 20th International Society for Music Information Retrieval Conference (ISMIR 2019), 2019

A Convolutional Approach to Melody Line Identification in Symbolic Scores

Author(s): Federico Simonetta, Carlos Cancino-Chacon, Stavros Ntalampiras, Gerhard Widmer
Published in: Proceedings of the 20th International Society for Music Information Retrieval Conference (ISMIR 2019), 2019

Linking and Visualising Performance Data and Semantic Music Encodings in Real Time

Author(s): David Weigl, Carlos Cancino Chacón, Martin Bonev, Werner Goebl
Published in: Late breaking / demo papers, 20th International Society for Music Information Retrieval Conference (ISMIR 2019), 2019

partitura: A Python Package for Handling Symbolic Musical Data

Author(s): Maarten Grachten, Carlos Eduardo Cancino-Chacon, Thassilo Gadermaier
Published in: Late breaking / demo papers, 20th International Society for Music Information Retrieval Conference (ISMIR 2019), 2019

Audio-Conditioned U-Net for Position Estimation in Full Sheet Images

Author(s): Florian Henkel, Rainer Kelz, Gerhard Widmer
Published in: Proceedings of the International Workshop on Reading Music Systems (WoRMS) 2019, 2019

Emotion and Theme Recognition in Music with Frequency-Aware RF-Regularized CNNs

Author(s): Khaled Koutini, Shreyan Chowdhury, Verena Haunschmid, Hamid Eghbal-zadeh, Gerhard Widmer
Published in: Proceedings of the MediaEval 2019 Multimedia Benchmark Workshop, 2019

Basis Function Modeling of Loudness Variations in Ensemble Performance

Author(s): Thassilo Gadermaier, Maarten Grachten, Carlos Eduardo Cancino-Chacon
Published in: Proceedings of the 2nd International Conference on New Music Concepts (ICNMC 2016), 2016

Real-time Visualization of Fugue Played by a String Quartet

Author(s): Olivier Lartillot, Carlos Eduardo Cancino-Chacon, Charles Brazier
Published in: Proceedings of the 17th Sound and Music Computing Conference (SMC 2020), 2020

On the Futility of Learning Complex Frame-Level Language Models for Chord Recognition

Author(s): Filip Korzeniowski, Gerhard Widmer
Published in: Proceedings of the 2017 AES International Conference on Semantic Audio, 2017

An Experimental Analysis of the Entanglement Problem in Neural-Network-based Music Transcription Systems

Author(s): Rainer Kelz, Gerhard Widmer
Published in: Proceedings of the 2017 AES International Conference on Semantic Audio, 2017

End-to-End Musical Key Estimation Using a Convolutional Neural Network

Author(s): Filip Korzeniowski, Gerhard Widmer
Published in: Proceedings of the 25th European Signal Processing Conference (EUSIPCO-2017), 2017

Modeling Harmony with Skip-Grams

Author(s): David Sears, Andreas Arzt, Harald Frostel, Reinhard Sonnleitner, Gerhard Widmer
Published in: Proceedings of the 18th International Society for Music Information Retrieval Conference (ISMIR 2017), 2017

From Bach to the Beatles: The Simulation of Human Tonal Expectation Using Ecologically-trained Predictive Models

Author(s): Carlos Eduardo Cancino-Chacon, Maarten Grachten, Kat Agres
Published in: Proceedings of the 18th International Society of Music Information Retrieval Conference (ISMIR 2017), 2017

Automatic Estimation of Harmonic Tension by Distributed Representation of Chords

Author(s): Ali Nikrang, David Sears, Gerhard Widmer
Published in: Proceedings of the 13th International Symposium on Computer Music Multidisciplinary Research (CMMR), 2017

Learning Audio - Sheet Music Correspondences for Score Identification and Offline Alignment

Author(s): Matthias Dorfer, Andreas Arzt, Gerhard Widmer
Published in: Proceedings of the 18th International Society for Music Information Retrieval Conference (ISMIR 2017), 2017

Aktuelle Entwicklungen in der automatischen Musikverfolgung

Author(s): Andreas Arzt and Matthias Dorfer
Published in: DGI Workshop: Musik trifft Informatik; 47. Jahrestagung der Gesellschaft fuer Informatik (GI), 2017

Piece Identification in Classical Piano Music Without Reference Scores

Author(s): Andreas Arzt and Gerhard Widmer
Published in: Proceedings of the 18th International Society for Music Information Retrieval Conference (ISMIR 2017), 2017

Learning Musical Relations using Gated Autoencoders

Author(s): Stefan Lattner, Maarten Grachten, Gerhard Widmer
Published in: Proceedings of the 2nd Conference on Computer Simulation of Musical Creativity (CSMC 2017), 2017

What were you expecting? Using Expectancy Features to Predict Expressive Performances of Classical Piano Music

Author(s): Carlos Eduardo Cancino-Chacon, Maarten Grachten, David Sears, and Gerhard Widmer
Published in: Proceedings of the 10th International Workshop on Machine Learning and Music (MML 2017), 2017

Learning to Read and Follow Music in Complete Score Sheet Images

Author(s): Florian Henkel, Rainer Kelz, Gerhard Widmer
Published in: Proceedings of the 21st International Society for Music Information Retrieval Conference (ISMIR 2020), 2020

Peer reviewed articles (13)

End-to-end cross-modality retrieval with CCA projections and pairwise ranking loss

Author(s): Matthias Dorfer, Jan Schlüter, Andreu Vall, Filip Korzeniowski, Gerhard Widmer
Published in: International Journal of Multimedia Information Retrieval, 2018, ISSN 2192-6611
DOI: 10.1007/s13735-018-0151-5

Imposing Higher-Level Structure in Polyphonic Music Generation Using Convolutional Restricted Boltzmann Machines and Constraints

Author(s): Stefan Lattner, Maarten Grachten, Gerhard Widmer
Published in: Journal of Creative Music Systems, Issue Volume 2, Issue 2, March 2018, 2018, ISSN 2399-7656

Learning Audio–Sheet Music Correspondences for Cross-Modal Retrieval and Piece Identification

Author(s): Matthias Dorfer, Jan Hajič jr., Andreas Arzt, Harald Frostel, Gerhard Widmer
Published in: Transactions of the International Society for Music Information Retrieval, Issue 1/1, 2018, Page(s) 22, ISSN 2514-3298
DOI: 10.5334/tismir.12

Cross-Modal Music Retrieval and Applications: An Overview of Key Methodologies

Author(s): Meinard Mueller, Andreas Arzt, Stefan Balke, Matthias Dorfer, Gerhard Widmer
Published in: IEEE Signal Processing Magazine, Issue 36/1, 2019, Page(s) 52-62, ISSN 1053-5888
DOI: 10.1109/msp.2018.2868887

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

Author(s): Carlos E. Cancino-Chacón, Maarten Grachten, Werner Goebl, Gerhard Widmer
Published in: Frontiers in Digital Humanities, Issue 5, 2018, Page(s) 1-25, ISSN 2297-2668
DOI: 10.3389/fdigh.2018.00025

Getting Closer to the Essence of Music

Author(s): Gerhard Widmer
Published in: ACM Transactions on Intelligent Systems and Technology, Issue 8/2, 2016, Page(s) 1-13, ISSN 2157-6904
DOI: 10.1145/2899004

Toward Computer-Assisted Understanding of Dynamics in Symphonic Music

Author(s): Maarten Grachten, Carlos Eduardo Cancino-Chacon, Thassilo Gadermaier, Gerhard Widmer
Published in: IEEE MultiMedia, Issue 24/1, 2017, Page(s) 36-46, ISSN 1070-986X
DOI: 10.1109/MMUL.2017.4

Eye gaze as a means of giving and seeking information during musical interaction

Author(s): Laura Bishop, Carlos Cancino-Chacón, Werner Goebl
Published in: Consciousness and Cognition, Issue 68, 2019, Page(s) 73-96, ISSN 1053-8100
DOI: 10.1016/j.concog.2019.01.002

Feature-combination hybrid recommender systems for automated music playlist continuation

Author(s): Andreu Vall, Matthias Dorfer, Hamid Eghbal-zadeh, Markus Schedl, Keki Burjorjee, Gerhard Widmer
Published in: User Modeling and User-Adapted Interaction, 2019, ISSN 0924-1868
DOI: 10.1007/s11257-018-9215-8

Moving to Communicate, Moving to Interact

Author(s): Laura Bishop, Carlos Cancino-Chacón, Werner Goebl
Published in: Music Perception: An Interdisciplinary Journal, Issue 37/1, 2019, Page(s) 1-25, ISSN 0730-7829
DOI: 10.1525/mp.2019.37.1.1

Score Following as a Multi-Modal Reinforcement Learning Problem

Author(s): Florian Henkel, Stefan Balke, Matthias Dorfer, Gerhard Widmer
Published in: Transactions of the International Society for Music Information Retrieval, Issue 2/1, 2019, Page(s) 67-81, ISSN 2514-3298
DOI: 10.5334/tismir.31

Beneath (or Beyond) the Surface: Discovering Voice-leading Patterns with Skip-grams

Author(s): David Sears, Gerhard Widmer
Published in: Journal of Mathematics and Music, 2020, ISSN 1745-9737

An evaluation of linear and non-linear models of expressive dynamics in classical piano and symphonic music

Author(s): Carlos Eduardo Cancino-Chacón, Thassilo Gadermaier, Gerhard Widmer, Maarten Grachten
Published in: Machine Learning, Issue 106/6, 2017, Page(s) 887-909, ISSN 0885-6125
DOI: 10.1007/s10994-017-5631-y

Other (1)

The Accompanion v0.1: An Expressive Accompaniment System

Author(s): Carlos Eduardo Cancino-Chacon, Martin Bonev, Amaury Durand, Maarten Grachten, Andreas Arzt, Laura Bishop, Werner Goebl, Gerhard Widmer
Published in: Late breaking / demo papers, 18th International Society for Music Information Retrieval Conference (ISMIR 2017), 2017

Thesis dissertations (8)

Harmonic Analysis of Musical Audio Using Deep Neural Networks

Author(s): Filip Korzeniowski
Published in: Ph.D. Thesis, 2018

A Regularization Study for Policy Gradient Methods

Author(s): Florian Henkel
Published in: Master's Thesis, 2018

Flexible and Robust Music Tracking

Author(s): Andreas Arzt
Published in: Ph.D. Thesis, 2016

Computational Modeling of Expressive Music Performance through Linear and Non-linear Basis Function Models

Author(s): Carlos Eduardo Cancino-Chacon
Published in: Ph.D. Thesis, 2018

Multimodal Deep Representation Learning and its Application to Audio and Sheet Music

Author(s): Matthias Dorfer
Published in: Ph.D. Thesis, 2018

Modeling Musical Structure with Artificial Neural Networks

Author(s): Stefan Lattner
Published in: Ph.D. Thesis, 2019

Automatic Music Accompaniment via On-line Time Warping and Kalman Filters

Author(s): Hannes Schauer
Published in: Master's Thesis, 2017

Machine Learning Approaches to Hybrid Music Recommender Systems

Author(s): Andreu Vall
Published in: Ph.D. Thesis, 2019