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!


ISMIR 2022
SampleMatch: Drum Sample Retrieval by Musical Context
Stefan Lattner
contrastive learning, drum samples selection, musical context
AIMC 2022
“Melatonin”: A Case Study on AI-induced Musical Style
Emmanuel Deruty, Maarten Grachten
musical style, bassnet, music production
ICML 2022 – MLAS Workshop
DrumGAN VST: A Plugin for Drum Sound Analysis/Synthesis with Autoencoding GANs
Javier Nistal, Cyran Aouameur, Ithan Velarde, Stefan Lattner
GANs, sound synthesis, drums, encoder
On the Development and Practice of AI Technology for Contemporary Popular Music Production
Emmanuel Deruty, Maarten Grachten, Stefan Lattner, Javier Nistal, Cyran Aouameur
AI music production, user study, development, popular music
The Piano Inpainting Application
Gaëtan Hadjeres, Léopold Crestel
piano inpainting, max for live, expressivity
ISMIR 2021
A Contextual Latent Space Model: Subsequence Modulation in Melodic Sequence
Taketo Akama
musical inpainting, latent spaces, subsequence modulation, context
ISMIR 2021
CRASH: Raw Audio Score-based Generative Modeling for Controllable High-resolution Drum Sound Synthesis
Simon Rouard, Gaëtan Hadjeres
drums generation, diffusion, high resolution
ISMIR 2021
DarkGAN: Exploiting Knowledge Distillation for Comprehensible Audio Synthesis with GANs
Javier Nistal, Stefan Lattner, Gaël Richard
knowledge distillation, GANs, audio tagging, controllable sound synthesis
Electronics 2021 (Special Issue)
Stochastic Restoration of Heavily Compressed Musical Audio Using Generative Adversarial Networks
Stefan Lattner, Javier Nistal
audio restoration, GANs
VQCPC-GAN: Variable-length Adversarial Audio Synthesis Using Vector-Quantized Contrastive Predictive Coding
Javier Nistal, Cyran Aouameur, Stefan Lattner, Gaël Richard
contrastive predictive coding, vector quantizagion, GAN conditionning, variable-length audio generation
AIMC 2020
Spectrogram Inpainting for Interactive Generation of Instrument Sounds
Théis Bazin, Gaëtan Hadjeres, Philippe Esling, Mikhail Malt
spectrogram inpainting, web interface, interaction, sound synthesis, VQVAE
Vector Quantized Contrastive Predictive Coding for Template-based Music Generation
Gaëtan Hadjeres, Léopold Crestel
self supervised learning, Bach chorales, control, variations, quantization
ISMIR 2020
Ultra-light deep MIR by trimming lottery tickets
Philippe Esling, Theis Bazin, Adrien Bitton, Tristan Carsault, Ninon Devis
mir, lottery ticket, pruning, deep learning, model compression
ISMIR 2020
DrumGAN: Synthesis of Drum Sounds With Timbral Feature Conditioning Using GANs
Javier Nistal, Stefan Lattner, Gaël Richard
drum synthesis, progressive growing GANs, perceptual features, control parameters
ISMIR 2020
Connective Fusion: Learning Transformational Joining of Sequences with Application to Melody Creation
Taketo Akama
sequence joining, latent space exploration, melody creation