activity
20182025
most citedUniversal audio synthesizer control with normalizing flows

34 citations · 108 across the 18 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2024

Unsupervised Composable Representations for Audio

Giovanni Bindi, Philippe Esling

Current generative models are able to generate high-quality artefacts but have been shown to struggle with compositional reasoning, which can be defined as the ability to generate…

cs.LG2022

Creative divergent synthesis with generative models

Axel Chemla--Romeu-Santos, Philippe Esling

Machine learning approaches now achieve impressive generation capabilities in numerous domains such as image, audio or video. However, most training \& evaluation frameworks revolv…

cs.LG20211 cited

Signal-domain representation of symbolic music for learning embedding spaces

Mathieu Prang, Philippe Esling

A key aspect of machine learning models lies in their ability to learn efficient intermediate features. However, the input representation plays a crucial role in this process, and…

cs.LG20214 cited

Energy Consumption of Deep Generative Audio Models

Constance Douwes, Philippe Esling, Jean-Pierre Briot

In most scientific domains, the deep learning community has largely focused on the quality of deep generative models, resulting in highly accurate and successful solutions. However…

cs.LG20201 cited

Ultra-light deep MIR by trimming lottery tickets

Philippe Esling, Theis Bazin, Adrien Bitton +2

Current state-of-the-art results in Music Information Retrieval are largely dominated by deep learning approaches. These provide unprecedented accuracy across all tasks. However, t…

cs.LG20204 cited

Diet deep generative audio models with structured lottery

Philippe Esling, Ninon Devis, Adrien Bitton +3

Deep learning models have provided extremely successful solutions in most audio application fields. However, the high accuracy of these models comes at the expense of a tremendous…