A Study on the Emotion Classification of the Speech Signal Using Support Vector Machine 


Vol. 46,  No. 10, pp. 1741-1749, Oct.  2021
10.7840/kics.2021.46.10.1741


PDF
  Abstract

This paper proposes an algorithm to classify the emotions of speech signals in constrained environments. The proposed algorithm used the SVM as a classifier, the Autocorrelation Function (ACF) was used to obtain pitch period, the Linear Predictive Coding (LPC) and Split-LPC were used to measure formant frequencies, and Zero Crossing Rate (ZCR) and Short Time Energy (STE) were used to determine voiced and unvoiced sounds. The experiment was conducted with voice data of three men and two women. In this paper, propose a method to add a process of gender classification before classifying emotions using SVMs to improve accuracy. Gender and emotional classification were graphically identified the relationship between pitch period and multiple formant frequencies. The proposed algorithm made improved accuracy emotion classification in constrained environments, and showed the potential to provide responses to the speaker’s discriminated emotions.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

J. Yeom, K. You, K. Jang, "A Study on the Emotion Classification of the Speech Signal Using Support Vector Machine," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 10, pp. 1741-1749, 2021. DOI: 10.7840/kics.2021.46.10.1741.

[ACM Style]

Jeong-seok Yeom, Kwang-Bock You, and Kyungnam Jang. 2021. A Study on the Emotion Classification of the Speech Signal Using Support Vector Machine. The Journal of Korean Institute of Communications and Information Sciences, 46, 10, (2021), 1741-1749. DOI: 10.7840/kics.2021.46.10.1741.

[KICS Style]

Jeong-seok Yeom, Kwang-Bock You, Kyungnam Jang, "A Study on the Emotion Classification of the Speech Signal Using Support Vector Machine," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 10, pp. 1741-1749, 10. 2021. (https://doi.org/10.7840/kics.2021.46.10.1741)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880