EMOTION DETECTION FROM VOICE BASED CLASSIFIED FRAME-ENERGY SIGNAL USING K-MEANS CLUSTERING

Nazia Hossain1, Rifat Jahan2, and Tanjila Tabasum Tunka3

1Senior Lecturer, Department of Computer Science & Engineering, Stamford University
Bangladesh, Dhaka, Bangladesh
2&3Undergraduate Student, Department of Computer Science & Engineering, Stamford
University Bangladesh, Dhaka, Bangladesh

ABSTRACT

Emotion detection is a new research era in health informatics and forensic technology. Besides having some challenges, voice based emotion recognition is getting popular, as the situation where the facial image is not available, the voice is the only way to detect the emotional or psychiatric condition of a person. However, the voice signal is so dynamic even in a short-time frame so that, a voice of the same person can differ within a very subtle period of time. Therefore, in this research basically two key criterion have been considered; firstly, this is clear that there is a necessity to partition the training data according to the emotional stage of each individual speaker. Secondly, rather than using the entire voice signal, short time significant frames can be used, which would be enough to identify the emotional condition of the speaker. In this research, Cepstral Coefficient (CC) has been used as voice feature and a fixed valued kmeans clustered method has been used for feature classification. The value of k will depend on the number of emotional situations in human physiology is being an evaluation. Consequently, the value of k does not necessarily consider the volume of experimental dataset. In this experiment, three emotional conditions: happy, angry and sad have been detected from eight female and seven male voice signals. This methodology has increased the emotion detection accuracy rate significantly comparing to some recent works and also reduced the CPU time of cluster formation and matching.

KEYWORDS

Cepstral Coefficient (CC), Emotion Detection Accuracy, Mel Frequency Cepstral Coefficient (MFCC), Vector Quantization (VQ), k-means Clustering.









Comments

Post a Comment

Popular posts from this blog

International Journal of Software Engineering & Applications(IJSEA)

Image
  Submit Your Articles...!!! Welcome to IJSEA International Journal of Software Engineering & Applications(IJSEA) ISSN:0975-3834 [Online]; 0975-4679 [Print] H-Index 36 Web Page URL : https://airccse.org/journal/ijsea/ijsea.html Current Issue ====================== November 2025, Volume 16, Number 6 https://www.airccse.org/journal/ijsea/vol16.html Intelligence as a Feature: Modeling ML in Software Product Lines Luz-Viviana Cobaleda1, Andres Lopez1,2, Paola Vallejo3, Raul Mazo2 and Julian Carvajal1 1Universidad de Antioquia, Colombia, 2Francia, 3Universidad EAFIT, Colombia https://aircconline.com/ijsea/V16N6/16625ijsea01.pdf A Smart Framework for Aligning College Curricula with Labor Market Needs Khaled Ebrahim Almajed, Hazem M. El-Bakry, Samir Abd Elrazez, Rasha Elhadri, Mansoura University, Egypt https://aircconline.com/ijsea/V16N6/16625ijsea02.pdf #ai #artificialintelligence #machinelearning #ml #deeplearning #genai #generativeai #aiineducation #edtechtools #...
Read more

International Journal of Software Engineering & Applications (IJSEA)

Image
 * Registration is currently open * International Journal of Software Engineering & Applications (IJSEA) H-INDEX - 36 ** ERA Indexed ** Submission Deadline: January 03, 2026 Webpage URL: https://airccse.org/journal/ijsea/ijsea.html Submission URL : https://airccse.com/submissioncs/home.html Contact Us : ijseajournal@airccse.org or ijsea@aircconline.com #softwaredevelopment #softwaredeveloper #SoftwareEngineering #softwareengineer #FullStack #DataScience #software #opensource #Cybersecurity #app #technology #cloudcomputing #coding #erpsoftware #webseries #businessdevelopment #developers #Business #technology #programming #security #webdeveloper #InnovationInEducation #softwareengineer #system
Read more

Generic Modelling Using Uml Extensions for Queens Challenge Puzzle Game From 1 to 25 Levels System

Image
Paper Title: Generic Modelling Using Uml Extensions for Queens Challenge Puzzle Game From 1 to 25 Levels System Authors: Hussain Mohammad Abu-Dalbouh, Ghadeer AlJibreen and Nehal AlDowighri, Qassim University, Kingdom of Saudi Arabia Abstract: The Unified Modeling Language (UML) is a language for the specification, visualization, and documentation of object-oriented software systems. Existing UML diagrams can be used to conveniently model behavior, but these diagrams can be hardly used to model games. However, UML cannot describe in an explicit manner the games requirements needed for modeling Queens Challenge Game. In this study, the modeling of queens challenge puzzle from 1 to 25 levels is discussed, the proposed extension to UML covering the use case diagram, sequence diagram, activity diagram and class diagram aspects of proposed at the various views and diagrams of the UML. The use of queens challenge game is illustrated using a queens challenge puzzle from 1 to 25 levels example...
Read more