34 citations · 108 across the 18 of their papers we have counts for
8 papers · 1 filter
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…
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…
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…
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…
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…
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…