Publications.

Diff-A-Riff: Musical Accompaniment Co-creation via Latent Diffusion Models

Music2Latent: Consistency Autoencoders for Latent Audio Compression 

Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation

Controlling Surprisal in Music Generation via Information Content Curve Matching 

Deep Learning-based Audio Representations for the Analysis and Visualisation of Timbre in Electronic Dance Music DJ Mixes

Investigating Design Choices in Joint-Embedding Predictive Architectures for General Audio Representation Learning

Bass Accompaniment Generation via Latent Diffusion

Self-Supervised Music Source Separation Using Vector-Quantized Source Category Estimates

Singer Identity Representation Learning Using Self-Supervised Techniques

Exploring Sampling Techniques for Generating Melodies with a Transformer Language Model

PESTO: Pitch Estimation with Self-supervised Transposition-equivariant Objective

GANStrument: Adversarial Instrument Sound Synthesis with Pitch-Invariant Instance Conditioning

On the Typicality of Musical Sequences

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

SampleMatch: Drum Sample Retrieval by Musical Context