Robust Emotion Recognition using Spectral and Prosodic Features

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.

List of contents

Introduction.- Robust Emotion Recognition using Pitch Synchronous and Sub-syllabic Spectral Features.- Robust Emotion Recognition using Word and Syllable Level Prosodic Features.- Robust Emotion Recognition using Combination of Excitation Source, Spectral and Prosodic Features.- Robust Emotion Recognition using Speaking Rate Features.- Emotion Recognition on Real Life Emotions.- Summary and Conclusions.- MFCC Features.- Gaussian Mixture Model (GMM).

About the author

K. Sreenivasa Rao is at Indian Institute of Technology, Kharagpur, India.
Shashidhar G, Koolagudi is at Graphic Era University, Dehradun, India.

Summary

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.

Product details

• Authors: Shashidhar G Koolagudi, Shashidhar G. Koolagudi, K Sreenivas Rao, K Sreenivasa Rao, K. Sreenivasa Rao
• Publisher: Springer, Berlin
• Languages: English
• Product format: Paperback / Softback
• Released: 18.12.2012
• EAN: 9781461463597
• ISBN: 978-1-4614-6359-7
• No. of pages: 118
• Dimensions: 172 mm x 236 mm x 9 mm
• Weight: 221 g
• Illustrations: XII, 118 p. 37 illus., 15 illus. in color.
• Series: SpringerBriefs in Speech Technology; SpringerBriefs in Electrical and Computer Engineering; SpringerBriefs in Electrical and Computer Engineering / SpringerBriefs in Speech Technology; SpringerBriefs in Electrical and Computer Engineering; SpringerBriefs in Speech Technology
• Subjects: Humanities, art, music > Linguistics and literary studies > General and comparative linguistics; Natural sciences, medicine, IT, technology > Technology > Electronics, electrical engineering, communications engineering