Robust Emotion Recognition using Spectral and Prosodic Features

You must be logged in to access this title.

Sign up now

Already a member? Log in

Synopsis

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.

Book details

Edition:
2013
Series:
SpringerBriefs in Speech Technology
Author:
K. Sreenivasa Rao, Shashidhar G. Koolagudi
ISBN:
9781461463603
Related ISBNs:
9781461463597
Publisher:
Springer New York
Pages:
N/A
Reading age:
Not specified
Includes images:
Yes
Date of addition:
2021-01-04
Usage restrictions:
Copyright
Copyright date:
2013
Copyright by:
Springer New York, New York, NY 
Adult content:
No
Language:
English
Categories:
Computers and Internet, Language Arts, Nonfiction, Technology