Analysis of Concealed Anger Emotion in a Neutral Speech Signal

Vamsi Vijay Mohan Dattada, M. Jeevan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Conventional standard emotion recognition systems do not apply well for the analysis of true emotional state, mostly because in standard emotion analysis the emotional state of a person is recognised over the complete utterance considering that emotions are mutually exclusive where as in real time it can also be a combination of emotions with a concealed emotion. Machine detecting these concealed information of emotion is important for emotional intelligence. It has wide applications in healthcare, aviation and defence. Statistical measures (central tendency of mean measure of spread) of autocorrelated pitch are used as features for analysing the progression of concealed emotion. The analysis of concealed emotion is performed over the synthesised concealed emotional speech signal. This speech signal is synthesised using the standard emotional speech signals (anger and neutral) from Berlin Emotional Speech (BES) database. T- statistic likelihood is used as measure for analysis of concealed emotion progressing over the synthesised speech signal. This framework is shown to provide a good tracking of emotional progressions over the synthesised concealed emotional speech signal.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics, DISCOVER 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728137353
DOIs
Publication statusPublished - 08-2019
Event3rd IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics, DISCOVER 2019 - Manipal, India
Duration: 11-08-201912-08-2019

Publication series

Name2019 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics, DISCOVER 2019 - Proceedings

Conference

Conference3rd IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics, DISCOVER 2019
Country/TerritoryIndia
CityManipal
Period11-08-1912-08-19

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Hardware and Architecture
  • Decision Sciences (miscellaneous)
  • Information Systems and Management
  • Electrical and Electronic Engineering
  • Computational Mathematics
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Analysis of Concealed Anger Emotion in a Neutral Speech Signal'. Together they form a unique fingerprint.

Cite this