Representing environmental sounds using the separable scattering transform

Carlo Baugé (1) , Mathieu Lagrange (2) , Joakim Andén (3) , Stéphane Mallat (3)

1 IRCAM - Institut de Recherche et Coordination Acoustique/Musique
2 IRCCyN - Institut de Recherche en Communications et en Cybernétique de Nantes
3 LIENS - Laboratoire d'informatique de l'école normale supérieure

Environmental sounds are an interesting subject of study for machine audition because of their wide variety of acousti-cal characteristics and their central presence in our everyday life. They are perceived effortlessly in the human auditory system whereas state-of-the-art computational systems are far from reaching the same efficiency. In this paper we propose a novel representation of such sounds based on the scattering transform which has the property of stability to time-warping deformations and invariance to time-shift useful for classifications tasks. This representation is compared to several state-of-the-art approaches for the task of quantifying similarity between environmental sounds.

Mots clés: scattering; separable scattering; wavelet; environmental sounds; similarity

Domaines: Machine Learning [stat.ML]

Carlo Baugé, Mathieu Lagrange, Joakim Andén, Stéphane Mallat. Representing environmental sounds using the separable scattering transform. ICASSP, May 2013, Vancouver, Canada. ⟨10.1109/ICASSP.2013.6639358⟩. ⟨hal-01126650⟩