A comprehensive survey on features and methods for speech emotion detection

Title

A comprehensive survey on features and methods for speech emotion detection

Creator

Alva M.Y.; Nachamai M.; Paulose J.

Description

Human computer interaction will be natural and effective when the interfaces are sensitive to human emotion or stress. Previous studies were mainly focused on facial emotion recognition but speech emotion detection is gaining importance due its wide range of applications. Speech emotion recognition still remains a challenging task in the field of affective computing as no defined standards exist for emotion classification. Speech signal carries large information related to the emotions conveyed by a person. Speech recognition system fails miserably if robust techniques are not implemented to address the variations in speech due to emotion. Emotion detection from speech has two main steps. They are feature extraction and classification. The goal of this paper is to give an overview on the types of corpus, features and classification techniques that are associated with speech emotion recognition. 2015 IEEE.

Source

Proceedings of 2015 IEEE International Conference on Electrical, Computer and Communication Technologies, ICECCT 2015

Date

2015-01-01

Publisher

Institute of Electrical and Electronics Engineers Inc.

Subject

classification methods; Emotion recognition; speech corpus; speech features

Coverage

Alva M.Y., Department of Computer Science, Christ University, Bangalore, India; Nachamai M., Department of Computer Science, Christ University, Bangalore, India; Paulose J., Department of Computer Science, Christ University, Bangalore, India

Rights

Restricted Access

Relation

ISBN: 978-147996084-2

Format

Online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1109/ICECCT.2015.7226047

https://www.scopus.com/inward/record.uri?eid=2-s2.0-84954113948&doi=10.1109%2fICECCT.2015.7226047&partnerID=40&md5=79c9b7a62b66eec6d27063b52ea139b4