Speaker state recognition using an HMM-based feature extraction method

In this article we present an efficient approach to modeling the acoustic features for the tasks of recognizing various paralinguistic henomena. Instead of the standard scheme of adapting the Universal Background Model (UBM), represented by the Gaussian ixture Model (GMM), normally used to model the frame-level acoustic features, we propose to represent the UBM by building monophone-based Hidden Markov Model (HMM). We present two approaches: transforming the monophone-based segmented MM–UBM to a GMM–UBM and proceeding with the standard adaptation scheme, or to perform the adaptation directly on he HMM–UBM. Both approaches give superior results than the standard adaptation scheme (GMM–UBM) in both the emotion ecognition task and the alcohol detection task. Furthermore, with the proposed method we were able to achieve better results than he current state-of-the-art systems in both tasks. 2012 Elsevier Ltd. All rights reserved.