Feature extraction of speech signal and heartbeat detection in angry emotion identification

Mohamed, Masnani and Lee, Chee Chuan and Ahmad, Ida Laila (2013) Feature extraction of speech signal and heartbeat detection in angry emotion identification. International Journal of Computer Science and Electronics Engineering (IJCSEE), 1 (1). pp. 101-106. ISSN 2320 –401X

[img] Text
AJ 2017 (77a) Feature extraction of speech signal.pdf
Restricted to Registered users only

Download (666kB) | Request a copy


Angry is one of emotions that play an essential role in decision making, perception, learning and more. This paper detects the angry emotion by analyzing and recognizing angry speech signal as well as detecting the heartbeat condition. The speech database was uttered by various speakers in different gender and emotions. For the analyzing experiment, several digital signal processing methods such as autocorrelation and linear predication technique was introduced to analyze the features. Then, Artificial Neural Network (ANN) was used to classify each parameter features such as mean fundamental frequency, maximum fundamental frequency, standard deviation fundamental frequency, mean amplitude, pause length ratio and first formant frequency to recognize the emotion. Meanwhile, a heartbeat monitoring circuit was developed to measure the heartbeat. The accuracy of the result has achieved over than 80 percent during emotional recognition test. This method can be used further to recognize angry emotion of patient during counseling session.

Item Type: Article
Uncontrolled Keywords: Artificial neural network; Digital signal processing; Emotions; Emotional speech signal and heartbeat
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800-8360 Electronics
Divisions: Faculty of Electrical and Electronic Engineering > Department of Electronic Enngineering
Depositing User: Mrs. Siti Noraida Miskan
Date Deposited: 18 Nov 2021 06:24
Last Modified: 18 Nov 2021 06:24
URI: http://eprints.uthm.edu.my/id/eprint/3544

Actions (login required)

View Item View Item