The final workshop includes presentations by the fellows of the main results of their research over the last three years as well as keynotes by several distinguished researchers in the field (announcement).
Keynotes
Applications of Machine Intelligence in Computational Acoustics Augusto Sarti, Politecnico di Milano YouTube
Source Separation Metrics: What are they really capturing? Rachel Bittner, Spotify
Generative Modeling Meets Deep Learning: A Modern Statistical Approach to Music Signal Analysis Kazuyoshi Yoshii, Kyoto University YouTube
Fellows’ Presentations
October 14
Data-Driven Musical Version Identification: Accuracy, Scalability, and Bias Perspectives Furkan Yesiler, Universitat Pompeu Fabra YouTube
Deep Learning Methods for Musical Instrument Separation and Recognition Carlos Lordelo, Queen Mary University of London & DoReMIR YouTube
Informed Audio Source Separation with Deep Learning in Limited Data Settings Kilian Schulze-Forster, Telecom Paris YouTube
Deep Neural Networks for Automatic Lyrics Transcription Emir Demirel, Queen Mary University of London YouTube
Data-Driven Approaches for Query by Vocal Percussion Alejandro Delgado, Queen Mary University of London & Roli YouTube
Towards Neural Context-Aware Performance-Score Synchronization Ruchit Agrawal, Queen Mary University of London
Autonomous and Robust Live Tracking of Complete Opera Performances Charles Brazier, Johannes Kepler University Linz YouTube
Large-Scale Multi-Modal Music Search and Retrieval without Symbolic Representation Luís Carvalho, Johannes Kepler University Linz YouTube
Investigating the Behaviour of Audio Classification Models through Adversarial Attacks and Gradient based Interpretability Methods Vinod Subramanian, Queen Mary University of London YouTube
October 15
Exploration of Music Collections with Audio Embeddings Philip Tovstogan, Universitat Pompeu Fabra PDF
Audio Auto-tagging as Proxy for Contextual Music Recommendation Karim Ibrahim, Telecom Paris YouTube
Deep Learning Methods for Music Style Transfer Ondřej Cífka, Telecom Paris YouTube
Exploring Generative Adversarial Networks for Controllable Musical Audio Synthesis Javier Nistal, Telecom Paris & Sony CSL YouTube
Neuro-Steered Music Source Separation Giorgia Cantisani, Telecom Paris YouTubePDF
Automatic Characterization and Generation of Music Loops and Instrument Samples for Electronic Music Production António Ramires, Universitat Pompeu Fabra YouTube