Logo Sony

We are always looking forward to having PhD interns on the team. If you are a PhD student interested in our activities, feel free to contact us!


Applied Sciences 2020 (Special Issue)
BassNet: A Variational Gated Autoencoder for Conditional Generation of Bass Guitar Tracks with Learned Interactive Control
Maarten Grachten, Stefan Lattner, Emmanuel Deruty
conditional bassline generation, gated autoencoder, features prediction, latent space exploration
Comparing Representations for Audio Synthesis Using Generative Adversarial Networks
Javier Nistal, Stefan Lattner, Gaël Richard
audio representation, GANs, sound synthesis, comparative study
ISMIR 2019
Learning Complex Basis Functions For Invariant Representations Of Audio
Stefan Lattner, Monika Dörfler, Andreas Arzt
complex autoencoder, transformation invariance, representation learning, music information retrieval
ISMIR 2019
Auto-adaptive Resonance Equalization using Dilated Residual Networks
Maarten Grachten, Emmanuel Deruty, Alexandre Tanguy
resonance equalization, subjective ratings
ISMIR 2019
Learning to Traverse Latent Spaces for Musical Score Inpainting
Ashis Pati, Alexander Lerch, Gaëtan Hadjeres
VAEs, music inpainting, latent space
DrumNet: High-Level Control of Drum Track Generation Using Learned Patterns of Rhythmic Interaction
Stefan Lattner, Maarten Grachten
drumnet, drum patterns, gated autoencoder, user control
ICCC 2019
NONOTO: A Model-agnostic Web Interface for Interactive Music Composition by Inpainting
Théis Bazin, Gaëtan Hadjeres
web interface, interactive music composition, music inpainting
ICCC 2019
Neural Drum Machine: An Interactive System for Real-time Synthesis of Drum Sounds
Cyran Aouameur, Philippe Esling, Gaëtan Hadjeres
VAE, drum synthesis, controlable system, latent space exploration
Variation Network: Learning High-level Attributes for Controlled Input Manipulation
Gaëtan Hadjeres, Frank Nielsen
VAE, latent space disentanglement, adversarial learning
On power chi expansions of f-divergences
Frank Nielsen, Gaëtan Hadjeres
f-divergences, chi-squared distance, exponential family, Taylor expansions, binomial and multinomial theorems, analytic formula, bounded density ratio
ISMIR 2018
A Predictive Model for Music Based on Learned Interval Representations
Stefan Lattner, Maarten Grachten, Gerhard Widmer
recurrent gated autoencoder, relative pitch modelling, interval representation
ISMIR 2018
Learning Transposition-Invariant Interval Features from Symbolic Music and Audio
Stefan Lattner, Maarten Grachten, Gerhard Widmer
repeated sections discovery, interval representation, transposition invariance
ISMIR 2018
Audio-to-Score Alignment using Transposition-invariant Features
Andreas Arzt, Stefan Lattner
audio-to-score alignment, gated autoencoder, local pitch intervals, transposition invariance
Neural Computing and Applications 2018
Anticipation-RNN: Enforcing Unary Constraints in Sequence Generation, with Application to Interactive Music Generation
Gaëtan Hadjeres, Frank Nielsen
automatic symbolic music generation, recurrent neural networks, interactive models, unary constraints
SSCI 2017
GLSR-VAE: Geodesic Latent Space Regularization for Variational Autoencoder Architectures
Gaëtan Hadjeres, François Pachet, Frank Nielsen
VAE, latent space regularization, disentaglement