Exploring Musical Possibilities via Machine Simulation

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Pubblicazioni

Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation

Autori: Florian Schmid, Khaled Koutini, Gerhard Widmer
Pubblicato in: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023, 2023
Editore: IEEE
DOI: 10.48550/arxiv.2211.04772

The match File Format: Encoding Alignments between Scores and Performances

Autori: Francesco Foscarin, Emmanouil Karystinaios, Silvan David Peter, Carlos Cancino-Chacón, Maarten Grachten, Gerhard Widmer
Pubblicato in: Proceedings of the Music Encoding Conference (MEC 2022), 2022
Editore: Tne Music Encoding Initiative (MEI)
DOI: 10.48550/arxiv.2206.01104

8+8=4: Formalizing Time Units to Handle Symbolic Music Durations

Autori: Emmanouil Karystinaios, Francesco Foscarin, Florent Jacquemard, Masahiko Sakai, Satoshi Tojo, Gerhard Widmer
Pubblicato in: Proceedings of the 16th International Symposium on Computer Music Multidisciplinary Research (CMMR 2023), 2023
Editore: Springer
DOI: 10.48550/arxiv.2310.14952

Cluster and Separate: A GNN Approach to Voice and Staff Prediction for Score Engraving

Autori: Francesco Foscarin, Emmanouil Karystinaios, Eita Nakamura, Gerhard Widmer
Pubblicato in: Proceedings of the 25th International Society for Music Information Retrieval Conference (ISMIR 2024), 2024
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2407.21030

Dilemmadata: On the Interoperability of Heterogeneous Roman Numeral Datasets

Autori: Johannes Hentschel, Emmanouil Karystinaios, Gerhard Widmer, Markus Neuwirth
Pubblicato in: Proceedings of the Music Encoding Conference (MEC 2026), 2026
Editore: Music Encoding Initiative (MEI)
DOI: 10.48550/arxiv.2606.31595

Precise and Simple Audio-to-Score Alignment

Autori: Silvan Peter, Patricia Hu, Gerhard Widmer
Pubblicato in: Proceedings of the Music Encoding Conference (MEC) 2026, 2026
Editore: Music Encoding Initiative (MEI)
DOI: 10.48550/arxiv.2605.20014

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

Autori: Carlos Cancino-Chacón, Silvan Peter, Patricia Hu, Emmanouil Karystinaios, Florian Henkel, Francesco Foscarin, Nimrod Varga, Gerhard Widmer
Pubblicato in: Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI-23), 2023
Editore: IJCAI
DOI: 10.48550/arxiv.2304.12939

EngravingGNN: A Hybrid Graph Neural Network for End-to-End Piano Score Engraving

Autori: Emmanouil Karystinaios, Francesco Foscarin, Gerhard Widmer
Pubblicato in: Proceedings of the International Conference on Technologies for Music Notation and Representation (TENOR), 2025
Editore: Central Conservatory of Music Beijing
DOI: 10.48550/arxiv.2509.19412

Are we describing the same sound? An Analysis of Word Embedding Spaces of Expressive Piano Performance

Autori: Silvan Peter, Shreyan Chowdhury, Carlos Cancino-Chacón, Gerhard Widmer
Pubblicato in: Proceedings of the Forum for Information Retrieval Evaluation (FIRE 2023), 2023
Editore: Association for Computing Machinery (ACM)
DOI: 10.1145/3632754.3632759

How Far Can Pretrained LLMs Go in Symbolic Music? Controlled Comparisons of Supervised and Preference-based Adaptation

Autori: Deepak Kumar, Emmanouil Karystinaios, Gerhard Widmer, Markus Schedl
Pubblicato in: Proceedings of the 4th Workshop on NLP for Music and Audio (NLP4MusA 2026), 2026
Editore: EACL
DOI: 10.48550/arxiv.2601.22764

Passage Summarization with Recurrent Models for Audio-Sheet Music Retrieval

Autori: Luis Carvalho, Gerhard Widmer
Pubblicato in: Proceedings of the 24th Conference of the International Society for Music Information Retrieval (ISMIR 2023), 2023
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2309.12111

Music Boomerang: Reusing Diffusion Models for Data Augmentation and Audio Manipulation

Autori: Alexander Fichtinger, Jan Schlüter, Gerhard Widmer
Pubblicato in: Proceedings of the 22nd Sound and Music Computing Conference (SMC 2025), 2025
Editore: Sound and Music Computing Initiative
DOI: 10.48550/arxiv.2507.04864

The GlueNote: Learned Representations for Robust and Flexible Note Alignment

Autori: Silvan Peter, Gerhard Widmer
Pubblicato in: Proceedings of the 25th International Society for Music Information Retrieval Conference (ISMIR 2024), 2024
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2408.04309

Are Inherently Interpretable Models More Robust? A Study in Music Emotion Recognition

Autori: Katharina Hoedt, Arthur Flexer, Gerhard Widmer
Pubblicato in: Proceedings of the 22nd Sound and Music Computing Conference (SMC 2025), 2025
Editore: Sound and Music Computing Initiative
DOI: 10.5281/zenodo.15837274

Partitura: A Python Package for Symbolic Music Processing

Autori: Carlos Cancino-Chacón, Silvan David Peter, Emmanouil Karystinaios, Francesco Foscarin, Maarten Grachten, Gerhard Widmer
Pubblicato in: Proceedings of the Music Encoding Conference (MEC 2022), 2022
Editore: The Music Encoding Initiative (MEI)
DOI: 10.48550/arxiv.2206.01071

Multi-Stage Music Source Restoration with BandSplit-RoFormer Separation and HiFi++ GAN

Autori: Tobias Morocutti, Emmanouil Karystinaios, Jonathan Greif, Gerhard Widmer
Pubblicato in: ICASSP 2026 Music Source Restoration (MSR) Challenge, 2026
Editore: ICASSP
DOI: 10.48550/arxiv.2603.04032

Estimating Musical Surprisal from Audio in Autoregressive Diffusion Model Noise Spaces

Autori: Mathias Rose Bjare, Stefan Lattner, Gerhard Widmer
Pubblicato in: Proceedings of the 26th International Society for Music Information Retrieval Conference (ISMIR), 2025
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2508.05306

The Rach3 Dataset: Towards Data-Driven Analysis of Piano Performance Rehearsal

Autori: Carlos Cancino-Chacón, Ivan Pilkov
Pubblicato in: Proceedings of the 30th International Conference on Multimedia Modeling (MMM 2024), 2024
Editore: Springer Verlag
DOI: 10.1007/978-3-031-56435-2_3

Decoding and Visualising Intended Emotion in an Expressive Piano Performance

Autori: Shreyan Chowdhury, Gerhard Widmer
Pubblicato in: 23rd International Society for Music Information Retrieval Conference (ISMIR 2022), Late-Breaking/Demo Papers, 2022
Editore: International Society for Music Information Retrieval (ISMIR)
DOI: 10.48550/arxiv.2303.01875

Beat this: Accurate Beat Tracking Without DBN Postprocessing

Autori: Francesco Foscarin, Jan Schlüter, Gerhard Widmer
Pubblicato in: Proceedings of the 25th International Society for Music Information Retrieval Conference (ISMIR 2024), 2024
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2407.21658

Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders

Autori: Mathias Rose Bjare, Giorgia Cantisani, Marco Pasini, Stefan Lattner, Gerhard Widmer
Pubblicato in: AI for Music Workshop, Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025), 2025
Editore: Neural Information Processing Systems Foundation
DOI: 10.48550/arxiv.2511.05350

A Study on the Data Distribution Gap in Music Emotion Recognition

Autori: Joann Ching, Gerhard Widmer
Pubblicato in: 17th International Symposium on Computer Music Multidisciplinary Research (CMMR) 2025, 2025
Editore: University College London
DOI: 10.48550/arxiv.2510.04688

AnalysisGNN: Unified Music Analysis with Graph Neural Networks

Autori: Emmanouil Karystinaios, Johannes Hentschel, Markus Neuwirth, Gerhard Widmer
Pubblicato in: 17th International Symposium on Computer Music Multidisciplinary Research (CMMR), 2025
Editore: University College London
DOI: 10.48550/arxiv.2509.06654

Sounding Out Reconstruction Error-Based Evaluation of Generative Models of Expressive Performance

Autori: Silvan Peter, Carlos Cancino-Chacón, Emmanouil Karystinaios, Gerhard Widmer
Pubblicato in: Proceedings of the 10th International Conference on Digital Libraries for Musicology (DLfM '23), 2023, Pagina/e 58-66
Editore: ACM
DOI: 10.1145/3625135.3625141

Discrete Diffusion Probabilistic Models for Symbolic Music Generation

Autori: Matthias Plasser, Silvan Peter, Gerhard Widmer
Pubblicato in: Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI-23), 2023
Editore: IJCAI

Exploring System Adaptations For Minimum Latency Real-Time Piano Transcription

Autori: Patricia Hu, Silvan David Peter, Jan Schlüter, Gerhard Widmer
Pubblicato in: Proceedings of the 26th International Society for Music Information Retrieval Conference (ISMIR 2025), 2025
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2509.07586

The Batik-plays-Mozart Corpus: Linking Performance to Score to Musicological Annotations

Autori: Patricia Hu, Gerhard Widmer
Pubblicato in: Proceedings of the 24th International Society for Music Information Retrieval Conference (ISMIR 2023), 2023
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2309.02399

"Concept-Based Techniques for ""Musicologist-friendly"" Explanations in a Deep Music Classifier"

Autori: Francesco Foscarin, Katharina Hoedt, Verena Praher, Arthur Flexer, Gerhard Widmer
Pubblicato in: Proceedings of the 23rd International Society for Music Information Retrieval Conference (ISMIR 2022), 2022
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2208.12485

Estimating Musical Surprisal in Audio

Autori: Mathias Rose Bjare, Giorgia Cantisani, Stefan Lattner, Gerhard Widmer
Pubblicato in: Proceedings of the 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2025), 2025
Editore: IEEE
DOI: 10.48550/arxiv.2501.07474

Exploring Sampling Techniques for Generating Melodies with a Transformer Language Model

Autori: Mathias Rose Bjare, Stefan Lattner, Gerhard Widmer
Pubblicato in: Proceedings of the 24th International Society for Music Information Retrieval Conference (ISMIR 2023), 2023
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2308.09454

Perception-Inspired Graph Convolution for Music Understanding Tasks

Autori: Emmanouil Karystinaios, Francesco Foscarin, Gerhard Widmer
Pubblicato in: Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI-24), 2024
Editore: International Joint Conferences on Artificial Intelligence, Inc. (IJCAI)
DOI: 10.48550/arxiv.2405.09224

Cadence Detection in Symbolic Classical Music using Graph Neural Networks

Autori: Emmanouil Karystinaios and Gerhard Widmer
Pubblicato in: Proceedings of the 23rd International Society for Music Information Retrieval Conference (ISMIR 2022), 2022
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2208.14819

Towards Robust and Truly Large-Scale Audio-Sheet Music Retrieval

Autori: Luis Carvalho, Gerhard Widmer
Pubblicato in: Proceedings of the IEEE 6th International Conference on Multimedia Information Processing and Retrieval (MIPR), 2023
Editore: IEEE
DOI: 10.48550/arxiv.2309.12158

SMUG-Explain: A Framework for Symbolic Music Graph Explanations

Autori: Emmanouil Karystinaios, Francesco Foscarin, Gerhard Widmer
Pubblicato in: Proceedings of the Sound and Music Computing Conference 2024 (SMC2024), 2024
Editore: Sound and Music Computing Network
DOI: 10.48550/arxiv.2405.09241

MUSE-Explainer: Counterfactual Explanations for Symbolic Music Graph Classification Models

Autori: Baptiste Hilaire, Emmanouil Karystinaios, Gerhard Widmer
Pubblicato in: 17th International Symposium on Computer Music Multidisciplinary Research (CMMR) 2025, 2025
Editore: University College London
DOI: 10.48550/arxiv.2509.26521

Predicting Music Hierarchies with a Graph-Based Neural Decoder

Autori: Francesco Foscarin, Daniel Harasim, Gerhard Widmer
Pubblicato in: Proceedings of the 24th International Society for Music Information Retrieval Conference (ISMIR 2023), 2023
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2306.16955

Self-Supervised Contrastive Learning for Robust Audio-Sheet Music Retrieval Systems

Autori: Luis Carvalho, Tobias Washüttl, Gerhard Widmer
Pubblicato in: Proceedings of the 14th ACM Conference on Multimedia Systems (MMSys 2023), 2023
Editore: Association for Computing Machinery (ACM)
DOI: 10.1145/3587819.3590968

How to Infer Repeat Structures in MIDI Performances

Autori: Silvan Peter, Patricia Hu, Gerhard Widmer
Pubblicato in: Proceedings of the Music Encoding Conference (MEC 2025), 2025
Editore: Music Encoding Initiative
DOI: 10.48550/arxiv.2505.05055

Differentiable Dictionary Search: Integrating Linear Mixing with Deep Non-Linear Modelling for Audio Source Separation

Autori: Lukas Samuel Martak, Rainer Kelz, Gerhard Widmer
Pubblicato in: Proceedings of the 24th International Congress on Acoustics (ICA 2022), 2022
Editore: International Commission for Acoustics (ICA)

Defending a Music Recommender Against Hubness-Based Adversarial Attacks

Autori: Katharina Hoedt, Arthur Flexer, Gerhard Widmer
Pubblicato in: Proceedings of the 19th Sound and Music Computing Conference (SMC 2022), 2022
Editore: Telecom Saint-Etienne
DOI: 10.5281/zenodo.6573391

Symbolic Music Representations for Classification Tasks: A Systematic Evaluation

Autori: Huan Zhang, Emmanouil Karystinaios, Simon Dixon, Gerhard Widmer, Carlos Eduardo Cancino-Chacón
Pubblicato in: Proceedings of the 24th International Society for Music Information Retrieval Conference (ISMIR 2023), 2023
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2309.02567

GraphMuse: A Library for Symbolic Music Graph Processing

Autori: Emmanouil Karystinaios, Gerhard Widmer
Pubblicato in: Proceedings of the 25th International Society for Music Information Retrieval Conference (ISMIR 2024), 2024
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2407.12671

Pairing Real-Time Piano Transcription with Symbol-level Tracking for Precise and Robust Score Following

Autori: Silvan Peter, Patricia Hu, Gerhard Widmer
Pubblicato in: Proceedings of the 22nd Sound and Music Computing Conference (SMC 2025), 2025
Editore: Sound and Music Computing Initiative
DOI: 10.48550/arxiv.2505.05078

Optical Music Recognition of Jazz Lead Sheets

Autori: Juan Carlos Martinez-Sevilla, Francesco Foscarin, Patricia Garcia-Iasci, David Rizo, Jorge Calvo-Zaragoza, Gerhard Widmer
Pubblicato in: Proceedings of the 26th International Society for Music Information Retrieval Conference (ISMIR 2025), 2025
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2509.05329

Towards Musically Informed Evaluation of Piano Transcription Models

Autori: Patricia Hu, Lukas Martak, Carlos Cancino-Chacon, Gerhard Widmer
Pubblicato in: Proceedings of the 25th International Society for Music Information Retrieval Conference (ISMIR 2024), 2024
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2406.08454

A Flexible Encoding Model for Non-Unique Note Alignments

Autori: Suhit Chiruthapudi, Adam Štefunko, Silvan Peter, Patricia Hu, Jan Hajič jr., Carlos Cancino-Chacón
Pubblicato in: Proceedings of the Music Encoding Conference (MEC 2026), 2026
Editore: Music Encoding Initiative (MEI)
DOI: 10.48550/arxiv.2606.28032

Exploring Performance-Complexity Trade-Offs in Sound Event Detection Models

Autori: Tobias Morocutti, Florian Schmid, Jonathan Greif, Francesco Foscarin, Gerhard Widmer
Pubblicato in: Proceedings of the 33rd European Signal Processing Conference (EUSIPCO 2025), 2025
Editore: IEEE
DOI: 10.48550/arxiv.2503.11373

Score-Agnostic Structure Analysis in Large-Scale Performance Datasets

Autori: Patricia Hu, Silvan Peter, Gerhard Widmer
Pubblicato in: Proceedings of the Music Encoding Conference (MEC) 2026, 2026
Editore: Music Encoding Initiative
DOI: 10.48550/arxiv.2605.25951

Online Symbolic Music Alignment with Offline Reinforcement Learning

Autori: Silvan Peter
Pubblicato in: Proceedings of the 24th International Society for Music Information Retrieval Conference (ISMIR 2023), 2023
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2401.00466

Controlling Surprisal in Music Generation via Information Content Curve Matching

Autori: Mathias Bjare, Stefan Lattner, Gerhard Widmer
Pubblicato in: Proceedings of the 25th International Society for Music Information Retrieval Conference (ISMIR 2024), 2023
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2408.06022

Learning General Audio Representations with Large-Scale Training of Patchout Audio Transformers

Autori: Khaled Koutini, Shahed Masoudian, Florian Schmid, Hamid Eghbal-zadeh, Jan Schlüter, Gerhard Widmer
Pubblicato in: Proceedings of HEAR 2021: Holistic Evaluation of Audio Representations, 2022, Pagina/e PMLR 166, 65-89, ISSN 2640-3498
Editore: JMLR, Inc.
DOI: 10.48550/arxiv.2211.13956

Music Visualisation and Its Short-Term Effect on Appraisal Skills

Autori: Ali Nikrang, Maarten Grachten, Martin Gasser, Harald Frostel, Gerhard Widmer, Tom Collins
Pubblicato in: HCI International 2023 – Late Breaking Papers. HCII 2023, 2023
Editore: Springer
DOI: 10.1007/978-3-031-48044-7_9

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

Autori: Emmanouil Karystinaios, Francesco Foscarin, Gerhard Widmer
Pubblicato in: Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023), 2023
Editore: IJCAI

Roman Numeral Analysis with Graph Neural Networks: Onset-wise Predictions from Note-wise Features

Autori: Emmanouil Karystinaios, Gerhard Widmer
Pubblicato in: Proceedings of the 24th International Society for Music Information Retrieval Conference (ISMIR 2023), 2023
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2307.03544

Language Models for Music Medicine Generation

Autori: Emmanouil Nikolakakis, Joann Ching, Emmanouil Karystinaios, Gabrielle Sipin, Gerhard Widmer, Razvan Marinescu
Pubblicato in: Extended Abstracts, Late-Breaking Demo Session, 25th International Society for Music Information Retrieval Conference (ISMIR 2024),, 2024
Editore: International Society for Music Information Retrieval
DOI: 10.48550/arxiv.2411.09080

Quantifying the Corpus Bias Problem in Automatic Music Transcription Systems

Autori: Lukas Samuel Martak, Patricia Hu, Gerhard Widmer
Pubblicato in: 1st International Workshop on Sound Signal Processing Applications (IWSSPA), 2024
Editore: CMMSE
DOI: 10.48550/arxiv.2408.04737

Concept-based Explanations for Music Emotion Recognition

Autori: Verena Praher, Verena Szojak, Gerhard Widmer
Pubblicato in: Proceedings of the 22nd Sound and Music Computing Conference (SMC 2025), 2025
Editore: Sound and Music Computing Initiative
DOI: 10.5281/zenodo.15837275

Expressivity-aware Music Performance Retrieval using Mid-level Perceptual Features and Emotion Word Embeddings

Autori: Shreyan Chowdhury, Gerhard Widmer
Pubblicato in: Proceedings of the Forum for Information Retrieval Evaluation Conference /(FIRE 2023), 2023
Editore: ACM

Revisiting Expressive Timing in Piano Performance at Scale: A Distant Listening, Multi‑Corpus Study

Autori: Patricia Hu, Huan Zhang, Silvan David Peter, Carlos Eduardo Cancino‑Chacón, Simon Dixon, Gerhard Widmer
Pubblicato in: Transactions of the International Society for Music Information Retrieval, Numero 9, 2026, Pagina/e 329-346, ISSN 2514-3298
Editore: Ubiquity Press, Ltd.
DOI: 10.5334/tismir.317

Time to Align! Modelling Musical Timelines for Music Information Retrieval and Digital Musicology

Autori: Johannes Hentschel, Axel Berndt, Carlos Cancino-Chacón, Simon Dixon, Anne Foo, Mark Gotham, Patricia Hu, Maik Köster, Felipe D. Martins, Davide A. Mauro, Meinard Müller, Markus Neuwirth, Alexander Pacha, Kevin R. Page, Silvan Peter, Egor Polyakov, Laurent Pugin, David M. Weigl, Christof Weiß, Gerhard Widmer
Pubblicato in: Transactions of the International Society for Music Information Retrieval, Numero 9, 2026, Pagina/e 384-404, ISSN 2514-3298
Editore: Ubiquity Press, Ltd.
DOI: 10.5334/tismir.296

Commentary on “A Computational Approach to the Detection and Prediction of (Ir)Regularity in Children’s Folk Songs”

Autori: Carlos Cancino-Chacón
Pubblicato in: Empirical Musicology Review, Numero 16(2), 2023, Pagina/e 328-335, ISSN 1559-5749
Editore: The Ohio State University Libraries
DOI: 10.18061/emr.v16i2.9159

Differentiable Short-Term Models for Efficient Online Learning and Prediction in Monophonic Music

Autori: Mathias Rose Bjare, Stefan Lattner, Gerhard Widmer
Pubblicato in: Transactions of the International Society for Music Information Retrieval, Numero 5(1), 2022, Pagina/e 190-207, ISSN 2514-3298
Editore: Ubiquity Press
DOI: 10.5334/tismir.123

Automatic Note-Level Score-to- Performance Alignments in the ASAP Dataset

Autori: Silvan Peter, Carlos Eduardo Cancino-Chacón, Francesco Foscarin, Andrew P. McLeod, Florian Henkel, Emmanouil Karystinaios, Gerhard Widmer
Pubblicato in: Transactions of the International Society for Music Information Retrieval, Numero 6(1), 2023, Pagina/e 27–42, ISSN 2514-3298
Editore: Ubiquity Press
DOI: 10.5334/tismir.149

Balancing Bias and Performance in Polyphonic Piano Transcription Systems

Autori: Lukas Samuel Martak, Rainer Kelz, Gerhard Widmer
Pubblicato in: Frontiers in Signal Processing, Numero 2:975932, 2022, ISSN 2673-8198
Editore: Frontiers Media SA
DOI: 10.3389/frsip.2022.975932

DExter: Learning and Controlling Performance Expression with Diffusion Models

Autori: Huan Zhang, Shreyan Chowdhury, Carlos Eduardo Cancino-Chacón, Jinhua Liang, Simon Dixon, Gerhard Widmer
Pubblicato in: Applied Sciences, Numero 14(15), 2024, Pagina/e 1-17, ISSN 2076-3417
Editore: MDPI
DOI: 10.3390/app14156543

Sound and music biases in deep music transcription models: a systematic analysis

Autori: Lukáš Samuel Marták, Patricia Hu, Gerhard Widmer
Pubblicato in: EURASIP Journal on Audio, Speech, and Music Processing, 2025, ISSN 1687-4722
Editore: Springer Science and Business Media LLC
DOI: 10.1186/s13636-025-00428-z

Dynamic Convolutional Neural Networks as Efficient Pre-Trained Audio Models

Autori: Florian Schmid, Khaled Koutini, Gerhard Widmer
Pubblicato in: IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024, ISSN 2329-9290
Editore: IEEE Advancing Technology for Humanity
DOI: 10.1109/taslp.2024.3376984

Constructing Adversarial Examples to Investigate the Plausibility of Explanations in Deep Audio and Image Classifiers

Autori: Katharina Hoedt, Verena Praher, Arthur Flexer, Gerhard Widmer
Pubblicato in: Neural Computing and Applications, Numero 2022, 2022, ISSN 0941-0643
Editore: Springer Verlag
DOI: 10.1007/s00521-022-07918-7

The Human Performance: Computational Methods for the Analysis of Played Classical Piano Music

Autori: Silvan Peter
Pubblicato in: 2025
Editore: Johannes Kepler University Linz

Symbolic Music Generation using Discrete Diffusion Probabilistic Models

Autori: Matthias Plasser
Pubblicato in: Master Thesis, 2023
Editore: Johannes Kepler University Linz (JKU)

(de)Fusion of Score and Performance Representations for Symbolic Music Generation

Autori: Tara Jadidi
Pubblicato in: Master Thesis, 2024
Editore: Johannes Kepler University (JKU)

Multi-modal Deep Learning for On-line Music Following in Score Sheet Images

Autori: Florian Henkel
Pubblicato in: PhD Thesis, 2022
Editore: Johannes Kepler University Linz

Multi-modal Music Search and Retrieval Without Symbolic Representations

Autori: Luis Carvalho
Pubblicato in: PhD Thesis, 2025
Editore: Johannes Kepler University

Modelling Emotional Expression in Music Using Interpretable and Transferable Perceptual Features

Autori: Shreyan Chowdhury
Pubblicato in: PhD Thesis, 2022
Editore: Johannes Kepler University Linz

Symbolic Music Analysis with Graph Neural Networks

Autori: Emmanouil Karystinaios
Pubblicato in: Ph.D. Thesis, 2024
Editore: Johannes Kepler University (JKU)

È in corso la ricerca di dati su OpenAIRE...

Risultati dei progetti

Pubblicazioni

Scarica Scarica il contenuto della pagina