Audio-based Event Recognition System for Smart Homes

Building an acoustic-based event recognition system for smart homes is a challenging task due to the lack of high-level structures in environmental sounds. In particular, the selection of effective features is still an open problem. We make an important step toward this goal by showing that the combination of Mel-Frequency Cepstral Coefficients, ZeroCrossing Rate, and Discrete Wavelet Transform features can achieve an F1 score of 96.5% and a recognition accuracy of 97.8% with a gradient boosting classifier for ambient sounds recorded in a kitchen environment. Keywords-Smart homes; assisted living; activity recognition; audio feature extraction; classification; mel-frequency; zerocrossing rate; wavelets;