Proceedings of the MULTINOVA: First International Conference on Artificial Intelligence in Engineering, Healthcare and Sciences (ICAIEHS- 2025)

<Previous Article In Volume
Next Article In Volume>

Explainable Machine Learning for Emotion Recognition from Speech Signals

Authors
G. M. Jeevapriya1, *, A. Rakshana Malya2, B. Subbulakshmi3, S. Prasanna4
1Computer Science and Engineering, Thiagarajar College of Engineering, Madurai, India
2Computer Science and Engineering, Thiagarajar College of Engineering, Madurai, India
3Computer Science and Engineering, Thiagarajar College of Engineering, Madurai, India
4Computer Science and Engineering, Thiagarajar College of Engineering, Madurai, India
*Corresponding author. Email: jeevapriyagm@gmail.com
Corresponding Author
G. M. Jeevapriya
Available Online 7 October 2025.
DOI
10.2991/978-94-6463-852-3_8How to use a DOI?
Keywords
Emotion Recognition; RF; KNN; LIME; XAI; Speech Signals; TESS Dataset
Abstract

Emotion recognition from speech improves human computer interaction by allowing machines to recognize and react to human feelings. Emotion classification using Kaggle’s TESS dataset is performed with RF, SVM, and KNN classifiers. To enhance audio quality and consistency, noise reduction, removal of silence, and resampling were implemented. The most important acoustic features, such as MFCC, Mel Spectrogram, and Chroma Features, were used to extract essential speech features. RF had the best accuracy of 99.29%, followed by KNN with 95%, which proved their efficacy in emotion recognition tasks. It also incorporated LIME to gain insights into the most significant features responsible for each prediction. This improved model transparency, enhancing reliability in real world use. By merging advanced ML methods with XAI, this method guarantees a stable and interpretable emotion recognition system to enable future developments in emotion aware human computer interaction.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the MULTINOVA: First International Conference on Artificial Intelligence in Engineering, Healthcare and Sciences (ICAIEHS- 2025)
Series
Advances in Intelligent Systems Research
Publication Date
7 October 2025
ISBN
978-94-6463-852-3
ISSN
1951-6851
DOI
10.2991/978-94-6463-852-3_8How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - G. M. Jeevapriya
AU  - A. Rakshana Malya
AU  - B. Subbulakshmi
AU  - S. Prasanna
PY  - 2025
DA  - 2025/10/07
TI  - Explainable Machine Learning for Emotion Recognition from Speech Signals
BT  - Proceedings of the MULTINOVA: First International Conference on Artificial Intelligence in Engineering, Healthcare and Sciences (ICAIEHS- 2025)
PB  - Atlantis Press
SP  - 121
EP  - 138
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-852-3_8
DO  - 10.2991/978-94-6463-852-3_8
ID  - Jeevapriya2025
ER  -