Early frame-based detection of acoustic scenes

Maxime Sangnier (1, 2) , Jérôme Gauthier (1) , Alain Rakotomamonjy (3)

1 LS2D (CEA, LIST) - Laboratoire Sciences des Données et de la Décision (CEA, LIST)
2 LTCI - Laboratoire Traitement et Communication de l'Information
3 DocApp - LITIS - Equipe Apprentissage

Let us consider a specific acoustic scene appearing in a continuous audio stream recorded while making a trip a in city. In this work, we aim at detecting at the earliest opportunity the several occurrences of this scene. The objective in early detection is then to build a decision function that is able to go off as soon as possible from the onset of a scene occurrence. This implies making a decision with an incomplete information. This paper proposes a novel framework in this area that i) can guarantee the decision made with a partial observation to be the same as the one with the full observation; ii) incorporates in a non-confusing manner the lack of knowledge about the minimal amount of information needed to make a decision. The proposed detector is based on mapping the temporal sequences to a landmarking space thanks to appropriately designed similarity functions. As a by-product, the built framework benefits from a scalable learning problem. A preliminary experimental study provides compelling results on a soundscape dataset.

Mots clés: acoustic scenes; frame-based detection; audio signal processing; acoustic signal processing; Acoustics; Reliability; Detectors; landmarking space; Early detection; event detection; scene analysis; classification; signal processing; artificial intelligence; machine learning; temporal sequences; scene occurrence; decision function; continuous audio stream

Domaines: Intelligence artificielle [cs.AI]; Traitement du signal et de l'image [eess.SP]; Recherche d'information [cs.IR]; Apprentissage [cs.LG]; Son [cs.SD]; Machine Learning [stat.ML]

Maxime Sangnier, Jérôme Gauthier, Alain Rakotomamonjy. Early frame-based detection of acoustic scenes. IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2015, Oct 2015, New Paltz, United States. pp.7336884, ⟨10.1109/WASPAA.2015.7336884⟩. ⟨hal-01890049⟩