Comparative Analysis of Speech Emotion Recognition Models and Technique

A. Agrawal; A. Jain; B. Kaur; S. Jangid; K. Kadian; V. Dwivedi; S. Garhwal

doi:10.1109/CICTN57981.2023.10141044

Comparative Analysis of Speech Emotion Recognition Models and Technique

A. Agrawal, A. Jain, B. Kaur, S. Jangid, K. Kadian, V. Dwivedi, S. Garhwal

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Speech Emotion Recognition (SER) refers to accurately predicting human emotions from their speech. The ability to predict emotions through speech signals is a motivating factor in achieving Human-Computer Interaction (HCI). This paper contains a comparative study of the existing research on speech emotion models. It makes use of the RAVDESS and SAVEE dataset containing audio input. The study of speech emotion recognition is made on SVM, CNN, KNN, MLP, Decision Tree, XGBoost, and Random Forest models. This paper presents a comparative analysis of the models highlighting the accuracy, F1 Score, bar plots, and loss graphs of the same. The paper also highlights the significant future areas for study in speech emotion recognition.

Original language	English
Title of host publication	2023 International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2023
Publisher	IEEE
Pages	499-505
Number of pages	7
ISBN (Electronic)	979-8-3503-3802-7, 979-8-3503-3803-4
DOIs	https://doi.org/10.1109/CICTN57981.2023.10141044
Publication status	Published (in print/issue) - 7 Jun 2023

Keywords

human computer interaction
support vector machine
Emotion Recognition
Analytical models
computational modeling
Speech recogniion
Forestry

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/CICTN57981.2023.10141044

260_CICTN2023

Cite this

@inproceedings{a0219d1a190c403bae124d02a23386fd,

title = "Comparative Analysis of Speech Emotion Recognition Models and Technique",

abstract = "Speech Emotion Recognition (SER) refers to accurately predicting human emotions from their speech. The ability to predict emotions through speech signals is a motivating factor in achieving Human-Computer Interaction (HCI). This paper contains a comparative study of the existing research on speech emotion models. It makes use of the RAVDESS and SAVEE dataset containing audio input. The study of speech emotion recognition is made on SVM, CNN, KNN, MLP, Decision Tree, XGBoost, and Random Forest models. This paper presents a comparative analysis of the models highlighting the accuracy, F1 Score, bar plots, and loss graphs of the same. The paper also highlights the significant future areas for study in speech emotion recognition.",

keywords = "human computer interaction, support vector machine, Emotion Recognition, Analytical models, computational modeling, Speech recogniion, Forestry",

author = "A. Agrawal and A. Jain and B. Kaur and S. Jangid and K. Kadian and V. Dwivedi and S. Garhwal",

year = "2023",

month = jun,

day = "7",

doi = "10.1109/CICTN57981.2023.10141044",

language = "English",

pages = "499--505",

booktitle = "2023 International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2023",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Comparative Analysis of Speech Emotion Recognition Models and Technique

AU - Agrawal, A.

AU - Jain, A.

AU - Kaur, B.

AU - Jangid, S.

AU - Kadian, K.

AU - Dwivedi, V.

AU - Garhwal, S.

PY - 2023/6/7

Y1 - 2023/6/7

N2 - Speech Emotion Recognition (SER) refers to accurately predicting human emotions from their speech. The ability to predict emotions through speech signals is a motivating factor in achieving Human-Computer Interaction (HCI). This paper contains a comparative study of the existing research on speech emotion models. It makes use of the RAVDESS and SAVEE dataset containing audio input. The study of speech emotion recognition is made on SVM, CNN, KNN, MLP, Decision Tree, XGBoost, and Random Forest models. This paper presents a comparative analysis of the models highlighting the accuracy, F1 Score, bar plots, and loss graphs of the same. The paper also highlights the significant future areas for study in speech emotion recognition.

AB - Speech Emotion Recognition (SER) refers to accurately predicting human emotions from their speech. The ability to predict emotions through speech signals is a motivating factor in achieving Human-Computer Interaction (HCI). This paper contains a comparative study of the existing research on speech emotion models. It makes use of the RAVDESS and SAVEE dataset containing audio input. The study of speech emotion recognition is made on SVM, CNN, KNN, MLP, Decision Tree, XGBoost, and Random Forest models. This paper presents a comparative analysis of the models highlighting the accuracy, F1 Score, bar plots, and loss graphs of the same. The paper also highlights the significant future areas for study in speech emotion recognition.

KW - human computer interaction

KW - support vector machine

KW - Emotion Recognition

KW - Analytical models

KW - computational modeling

KW - Speech recogniion

KW - Forestry

UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-85163191483&partnerID=MN8TOARS

U2 - 10.1109/CICTN57981.2023.10141044

DO - 10.1109/CICTN57981.2023.10141044

M3 - Conference contribution

SP - 499

EP - 505

BT - 2023 International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2023

PB - IEEE

ER -

Comparative Analysis of Speech Emotion Recognition Models and Technique

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this