Welcome to the InfoSci Platform
Reference Hub4
Speech Emotion Analysis of Different Age Groups Using Clustering Techniques

Speech Emotion Analysis of Different Age Groups Using Clustering Techniques

Hemanta Kumar Palo, Mihir Narayan Mohanty, Mahesh Chandra
Copyright: © 2018 |Volume: 8 |Issue: 1 |Pages: 17
ISSN: 2155-6377|EISSN: 2155-6385|EISBN13: 9781522545637|DOI: 10.4018/IJIRR.2018010105
Cite Article Cite Article

MLA

Palo, Hemanta Kumar, et al. "Speech Emotion Analysis of Different Age Groups Using Clustering Techniques." IJIRR vol.8, no.1 2018: pp.69-85. http://doi.org/10.4018/IJIRR.2018010105

APA

Palo, H. K., Mohanty, M. N., & Chandra, M. (2018). Speech Emotion Analysis of Different Age Groups Using Clustering Techniques. International Journal of Information Retrieval Research (IJIRR), 8(1), 69-85. http://doi.org/10.4018/IJIRR.2018010105

Chicago

Palo, Hemanta Kumar, Mihir Narayan Mohanty, and Mahesh Chandra. "Speech Emotion Analysis of Different Age Groups Using Clustering Techniques," International Journal of Information Retrieval Research (IJIRR) 8, no.1: 69-85. http://doi.org/10.4018/IJIRR.2018010105

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

The shape, length, and size of the vocal tract and vocal folds vary with the age of the human being. The variation may be of different age or sickness or some other conditions. Arguably, the features extracted from the utterances for the recognition task may differ for different age group. It complicates further for different emotions. The recognition system demands suitable feature extraction and clustering techniques that can separate their emotional utterances. Psychologists, criminal investigators, professional counselors, law enforcement agencies and a host of other such entities may find such analysis useful. In this article, the emotion study has been evaluated for three different age groups of people using the basic age- dependent features like pitch, speech rate, and log energy. The feature sets have been clustered for different age groups by utilizing K-means and Fuzzy c-means (FCM) algorithm for the boredom, sadness, and anger states. K-means algorithm has outperformed the FCM algorithm in terms of better clustering and lower computation time as the authors' results suggest.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.