Privacy aware acoustic scene synthesis using deep spectral feature inversion

Félix Gontier (1) , Mathieu Lagrange (1) , Catherine Lavandier (2, 3) , Jean-François Petiot (4)

1 LS2N - Laboratoire des Sciences du Numérique de Nantes
2 ETIS - UMR 8051 - Equipes Traitement de l'Information et Systèmes
3 Neurocybernétique
4 IRCCyN - Institut de Recherche en Communications et en Cybernétique de Nantes

Gathering information about the acoustic environment of urban areas is now possible and studied in many major cities in the world. Part of the research is to find ways to inform the citizen about its sound environment while ensuring her privacy. We study in this paper how this application can be cast into a feature inversion problem. We argue that considering deep learning techniques to solve this problem allows us to produce sound sketches that are representative and privacy aware. Experiments done considering the dcase2017 dataset shows that the proposed learning based approach achieves state of the art performance when compared to blind inversion approaches.

Mots clés: spectral feature inversion; privacy aware audio synthesis; deep neural network; environmental audio processing

Domaines: Machine Learning [stat.ML]; Traitement du signal et de l'image [eess.SP]; Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]; Multimédia [cs.MM]; Traitement du signal et de l'image [eess.SP]

Félix Gontier, Mathieu Lagrange, Catherine Lavandier, Jean-François Petiot. Privacy aware acoustic scene synthesis using deep spectral feature inversion. IEEE ICASSP, May 2020, Barcelona, Spain. ⟨10.1109/ICASSP40776.2020.9053172⟩. ⟨hal-02478866⟩