CE23 - Intelligence artificielle et science des données

Audio Quality Analysis for Representing, Indexing and Unifying Signals – AQUA-RIUS

Submission summary

Audio quality is an important characteristic which conveys intrinsic information about the audio creation process from recording to the studio post-mastering effects. In a recent study, we developed a pioneered method to objectively extract signal features enabling us to predict the applied audio effects and the decade when a music track was created. Hence, AQUA-RIUS proposes an exhaustive investigation of audio quality through a deep learning methodology by addressing the 3 following scientific questions organized in tasks: 1)the analysis and modeling of audio quality, 2)audio quality simulation in a data augmentation machine learning framework to improve the robustness of the trained models and 3)the reverse engineering of audio mixture to allow audio document restoration and to control audio quality. The first rate expertise in signal processing and in deep learning of the 3 partners of the projects (IBISC, IRCAM, Telecom Paris) is a definite asset to tackle this project.

Project coordination

Dominique Fourer (Université d'Evry-Val d'Essonne)

The author of this summary is the project coordinator, who is responsible for the content of this summary. The ANR declines any responsibility as for its contents.


LTCI Telecom ParisTech
IBISC Université d'Evry-Val d'Essonne

Help of the ANR 510,157 euros
Beginning and duration of the scientific project: December 2022 - 42 Months

Useful links

Explorez notre base de projets financés



ANR makes available its datasets on funded projects, click here to find more.

Sign up for the latest news:
Subscribe to our newsletter