Modeling drivers' speech under stress

In this paper we explore the use of features derived from multiresolution analysis of speech and the Teager Energy Operator for classi cation of drivers' speech under stressed conditions. We apply this set of features to a database of short speech utterances to create userdependent discriminants of four stress categories. In addition we address the problem of choosing a suitable temporal scale for representing categorical di erences of the data. This leads to two sets of modeling techniques. In the rst approach, we model the dynamics of the feature set within the utterance with a family of dynamic classiers. In the second approach, we model the mean value of the features across the utterance with a family of static classi ers. We report and compare classi cation performances on the sparser and full dynamic representations for a set of four subjects.