Identification of sounds and sensing technology for home-care applications

This article focuses on an analysis of the needs of Hearing Impaired People and on the development of a recognition of environmental sounds system in a typical home. Based on the extraction of acoustic characteristics (Mel Frequency Cepstral Coefficients, Zero Crossing Rate, Roll Off Point and Spectral Centroid) and their combination with data from presence sensors, an accuracy rate of 88.4% was obtained.