Work

Comparative Analysis of Speech Emotion Recognition Models and Technique

Year: 2023

Type: conference-paper

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.

Source: International Conference on Computational Intelligence, Communication Technology and Networking (CICTN)

DOI: 10.1109/cictn57981.2023.10141044

Authors: Aditi Agrawal, Anagha Jain, Balpreet Kaur, Saumya Jangid, Karuna Kadian, Vimal Dwivedi, Sunita Garhwal

Institutions: Indira Gandhi Delhi Technical University for Women, Queen's University Belfast, University of Tartu

Language: English

Topic: Emotion and Mood Recognition

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4379619982

FWCI: 0.442

Cites: 18

Cited by: 4

Related to: 10