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

Publications.

NeurIPS Audio Imagination Workshop 2024
Improving Musical Accompaniment Co-Creation via Diffusion Transformers
Javier Nistal, Marco Pasini, Stefan Lattner
generative models, music, accompaniment, diffusion, consistency, autoencoders
NeurIPS Audio Imagination Workshop 2024
Continuous Autoregressive Models with Noise Augmentation Avoid Error Accumulation
Marco Pasini, Javier Nistal, Stefan Lattner
audio, generation, music, autoregressive, transformer
ISMIR 2024
Diff-A-Riff: Musical Accompaniment Co-creation via Latent Diffusion Models
Javier Nistal, Marco Pasini, Cyran Aouameur, Maarten Grachten, Stefan Lattner
latent diffusion, musical accompaniment, co-creator, high-quality
ISMIR 2024
Music2Latent: Consistency Autoencoders for Latent Audio Compression 
Marco Pasini, Stefan Lattner, George Fazekas
audio codec, compression, consistency diffusion, autoencoder
ISMIR 2024
Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation
Alain Riou, Stefan Lattner, Gaëtan Hadjeres, Michael Anslow, Geoffroy Peeters
First Keyword, Second Keyword, Third Keyword
ISMIR 2024
Harmonic and Transposition Constraints Arising from the Use of the Roland TR-808 Bass Drum
Emmanuel Deruty
speakers frequency response, tuning, contemporary popular music
ISMIR 2024
Controlling Surprisal in Music Generation via Information Content Curve Matching 
Mathias Bjare, Stefan Lattner, Gerhard Widmer
information content curves, surprise
AES International Symposium
Deep Learning-based Audio Representations for the Analysis and Visualisation of Timbre in Electronic Dance Music DJ Mixes
Alexander Williams, Haokun Tian, Stefan Lattner, Mathieu Barthet, Charalampos Saitis
transition timestamps, visualization, dataset annotations
ICASSP 2024
Investigating Design Choices in Joint-Embedding Predictive Architectures for General Audio Representation Learning
Alain Riou, Stefan Lattner, Gaëtan Hadjeres, Geoffroy Peeters
JEPA, self-supervised, representation learning, masked image modelling
ICASSP 2024
Bass Accompaniment Generation via Latent Diffusion
Marco Pasini, Maarten Grachten, Stefan Lattner
latent diffusion, diffusion sampling, music accompaniment generation
NeurIPS 2023 – MLA Workshop
Self-Supervised Music Source Separation Using Vector-Quantized Source Category Estimates
Marco Pasini, Stefan Lattner, George Fazekas
source separation, self-supervised learning, clustering
ISMIR 2023
Singer Identity Representation Learning Using Self-Supervised Techniques
Bernardo Torres, Stefan Lattner, Gael Richard
singer identity, representation learning, self-supervised
ISMIR 2023
Exploring Sampling Techniques for Generating Melodies with a Transformer Language Model
Mathias Rose Bjare, Stefan Lattner, Gerhard Widmer
transformers, sequence generation, typical sampling, folk melody
ISMIR 2023
PESTO: Pitch Estimation with Self-supervised Transposition-equivariant Objective
Alain Riou, Stefan Lattner, Gaëtan Hadjeres, Geoffroy Peeters
pitch estimation, Self Supervised Learning (SSL), lightweight, Toeplitz matrices
ICASSP 2023
GANStrument: Adversarial Instrument Sound Synthesis with Pitch-Invariant Instance Conditioning
Gaku Narita, Junichi Shimizu, Taketo Akama
neural synthesizer, generative adversarial networks, adversarial feature extraction