Robust Emotion Recognition using Spectral and Prosodic Features [Paperback]

In this brief, the authors discuss recently explored spectral (sub-segmental and pitch synchronous) and prosodic (global and local features at word and syllable levels in different parts of the utterance) features for discerning emotions in a robust manner.The authors also delve into the complementary evidences obtained from excitation source, vocal tract system and prosodic features for the purpose of enhancing emotion recognition performance. Features based on speaking rate characteristics are explored with the help of multi-stage and hybrid models for further improving emotion recognition performance. Proposed spectral and prosodic features are evaluated on real life emotional speech corpus.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . .. . . . . . . . . . . . . 11.2 Emotion from psychological perspective . . . . . . . . . . . . . . . . . . . .. . 21.3 Emotion from speech signal perspective . . . . . . . . . . . . . . .. . . . . . . 31.3.1 Speech production mechanism . . . . . . . . . . . . . . . . . . . . . . . . .... 41.3.2 Source features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41.3.3 System features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51.3.4 Prosodic features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 61.4 Emotional speech databases . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 61.5 Applications of speech emotion recognition . . . . . . . . . . . . . . . . . . . 81.6 Issues in speech emotion recognition . . . . . . . . . . . . . . . . . . . . . . . 81.7 Objectives and scope of the work . . . . . . . . . . . . . . . . . . . . . . . . .. 91.8 Main highlights of research investigations . . . . . . . . . . . . . . . . . . . 101.9 Brief overview of contributions in this book . . . . . . . . . . . . . . .. . . 101.9.1 Emotion recognl“7