期刊名称：Current Journal of Applied Science and Technology
印刷版ISSN：2457-1024
出版年度：2015
卷号：10
期号：5
页码：1-13
语种：English
出版社：Sciencedomain International
摘要：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.
