Cooking State Recognition based on Acoustic Event Detection

This paper conducts the cooking sound analysis for understanding cooking activities toward cooking support systems. Although there have been attempts to use images, accelerations or temperature sensors to understand cooking behavior, only limited studies have been conducted using acoustic signals. In this study, a data set was newly constructed by recording sounds generated from actual cooking processes and cooking state estimation was carried out based on the constructed data set. Two types of features, which are derived from mel-frequency cepstral coefficients (MFCC) analysis and non-negative matrix factorization (NMF), are examined, and the performance of classification based on Gaussian mixture models (GMM) incorporating these features is investigated.