Sound Detection and Classification for Medical Telesurvey

M Vacher (1) , D Istrate (1) , Laurent Besacier (1) , Jean-François Serignat (1) , E Castelli (2)

1 CLIPS-IMAG - Equipe GEOD, Groupe d'étude sur l'oral et le dialogue
2 MICA - Multimédia, Informations, Communication et Applications

Medical Telesurvey needs human operator assistance by smart information systems. This paper deals with the sound event detection in a noisy environment and presents a first classification approach. Detection is the first step of our sound analysis system and is necessary to extract the sig-nificant sounds before initiating the classification step. An algorithm based on the Wavelet Transform is evaluated in noisy environment. Then Wavelet based cepstral coeffi-cients are proposed and their results are compared with more classical parameters. Detection algorithm and sound classification methods are applied to medical telemonitor-ing. In our opinion, microphones surveying life sounds are better preserving patient privacy than video cameras.

Mots clés: Acoustical Signal Processing; Noise; Sound Detection; Sound Classification; Wavelet Transform

Domaines: Autre [cs.OH]

M Vacher, D Istrate, Laurent Besacier, Jean-François Serignat, E Castelli. Sound Detection and Classification for Medical Telesurvey. 2nd Conference on Biomedical Engineering, Feb 2004, Innsbrück, Austria. pp.395-398. ⟨hal-01088243⟩