Skip to content
Research Article Open access CC BY 4.0

Correlation of EEG Images and Speech Signals for Emotion Analysis

Priyanka A. Abhang, Bharti W. Gawali

Current Journal of Applied Science and Technology · pp. 1–13 · Published 6 Jul 2015

10.9734/BJAST/2015/19000

Abstract

Aims: The paper anticipates the correlation of EEG images and speech signals for understanding the emotions. Study Design: The study focuses on recognition of emotions using EEG images and speech signals using various image processing and statistical techniques. For correlating these two modalities, Person’s correlation coefficient is used. Place and Duration of Study: System Communication Machine Learning Research Lab (SCM-RL).Department of Computer Science and Information Technology, Dr. Babasaheb Ambedkar Marathwada   University, Aurangabad, India. 2009 - till date. Methodology: The study was performed using the data from 10 volunteers 5 boys and 5 girls, vocally sharing the experiences for happy and sad emotional states. Image processing techniques were employed to extract features from EEG images. A Threshold and Sobel Edge detection technique is used to extract the active regions of the brain during the emotional states.  MatlabR2012 is used to calculate the active size of EEG images. PRAAT software is used to extract the features of speech signals. Pitch, intensity and RMS energy parameters were used for the analysis of speech features.  The correlation is calculated using size of active region from EEG images with pitch and intensity for said emotional state. Results: The correlation of EEG images with speech signals is implemented using SPSS software using Person’s correlation coefficient with significance of about 95% which can further be inspected in results. Conclusion: The correlation of both EEG images and speech signals found to be between moderate to strong relationship and is signified through p value which is in the range of .001 to .081 in happy emotional state and .000 to .069 in sad emotional state. The results can be utilized in making the Robust Emotion Recognition System (ERS). This research study can also found to be significant in research domains like forensic science, psychology and many other applications of Brain Computer Interface.

BCI emotion recognition EEG speech processing EEG images correlation

Cited by 20

Multi-Modal Emotion Aware System Based on Fusion of Speech and Brain Information

Rania M. Ghoniem, Abeer D. Algarni, Khaled Shaalan · Information · 2019

Brain Electrical Activity Mapping in Military Pilots During Simulator Trainings

Petr Volf, Radek Doskocil, Miloslav Stehlik · 2019 International Conference on Military Technologies (ICMT) · 2019

Classification of EEG Signals Based on Image Representation of Statistical Features

Jodie Ashford, Jordan J. Bird, Felipe Campelo · Advances in Intelligent Systems and Computing · 2019

Analyzing Video Information by Monitoring Bioelectric Signals

Natalya Filatova, Konstantin Sidorov, Pavel Shemaev · Advances in Intelligent Systems and Computing · 2018

Modeling Physiological and Neuronal Systems

Jakub Sawicki · Current Research in Systematic Musicology · 2025

Continuous affect prediction using eye gaze and speech

Jonny O'Dwyer, Ronan Flynn, Niall Murray · 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · 2017

EEG Feature Significance Analysis

Yuhao Zhang, Yue Yao, Zakir Hossain · Communications in Computer and Information Science · 2021

Exploring Computational Thinking Perspectives in Black Communities with Physiological Computing

Myles Lewis, Amanda Holloman, Bryan Y. Hernández Cuevas · 2024 Black Issues in Computing Education (BICE) · 2024

Article metrics

Real usage data collected on this platform.

0

Page views

0

PDF downloads

0

Outbound clicks

20

Citations

Views by country

Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".

No views recorded yet.

Traffic sources

Referring site, by host.

No traffic recorded yet.

Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.