Search

International audience; This paper addresses a localization system which is based on a combination of information from two modalities: a Smart Home Person Tracking (SHPT) composed of infrared sensors and an Audio Person Tracking (APT) which uses microphones able to estimate azimuth of acoustic sources. This combination improves precision of localization compared to a standalone or separated module. The localization software facilitates the integration of both SHPT and APT systems, to display the position in real time, to record data and detect some distress situations (some kind of fall). Results on implementation show good adaptation for Smart Home environments and a robust detection

International audience; The use of Gaussian Mixture Models (GMM), adapted through the Expectation Minimization(EM)algorithm, is not rare in Audio Analysis for Surveillance Applications and Environmental sound recognition. Their use, at a first glance, is founded on the good qualities of GMM models when aimed at approximating Probability Density Functions(PDF) of random variables. But in some cases, where models are to be adapted from small sample sets of specific and locally recorded signals, instead of large but generic databases, a problem of balance between model complexity and sample size may play an important role. From this perspective, we show, through simple sound classification experiments, that constrained GMM, with fewer degrees of freedom, as compared to GMM with full covariance matrices, provide better classification performances. Moreover, pushing this argument even further, we also show that a Parzen model (seen here as an over-constrained GMM) can do even better than usual GMM, in terms of classification error ratio