Robust Emotion Recognition using Spectral and Prosodic Features

Description:

<p>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.</p><p>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.</p>

subjects: Engineering,  Translators (Computer programs),  Computer science,  Language Translation and Linguistics,  Image and Speech Processing Signal,  User Interfaces and Human Computer Interaction,  Computational linguistics,  Speech processing systems,  Pattern recognition systems,  Spectral analysis (Phonetics),  Prosodic analysis (Linguistics),  Linguistic analysis (linguistics)