SPEECH EMOTION RECOGNITION USING DEEP LEARNING

Vandana Singh

SPEECH EMOTION RECOGNITION USING DEEP LEARNING

May 2022

Vol-8, Issue-3

Paper ID: 16880

ISSN: 2395-4396

Downloads: 0

Abstract & Details

Research Area

Computer Science Engineering

Keywords

Emotion detection deep learning machine learning classification mel-frequency cepstral coefficients CNN RAVDESS TESS SVM MLP

Abstract

The purpose of this study is to detect the emotions evoked by the speaker while they are speaking. Speech generated in a condition of fear, rage, or delight, for example, becomes loud and quick, with a greater and broader range of pitch, but speech produced in a state of grief or exhaustion is sluggish and low-pitched. The detection of human emotions via voice and speech patterns has a variety of applications, including improving human-machine interactions. We provide a classification model of emotions produced by speeches that uses deep neural networks (CNNs), Support Vector Machine (SVM), and Multilayer Perceptron (MLP) Classification based on auditory data like Mel Frequency Campestral Coefficient (MFCC). . The models have been taught to distinguish between seven different emotions (neutral, calm, happy, sad, angry, fearful, disgust, surprise). Using the Ryerson Audio-Visual Dataset of Emotions Speech and Song (RAVDESS) dataset and the Toronto Emotional Speech Set (TESS) dataset, we found that the suggested technique achieves accuracies of 86 percent, 84 percent, and 82 percent using CNN, MLP, and SVM, respectively, for 7 emotions.

License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Author Information

#	Name	Institute / Affiliation
1	Vandana Singh	Integral University

How to Cite

Use the following formats to cite this article in your research.

APA Style

Singh, Vandana (2022). SPEECH EMOTION RECOGNITION USING DEEP LEARNING. International Journal of Advance Research and Innovative Ideas In Education, 8(3), 1921-1925.

MLA Style

Singh, Vandana. "SPEECH EMOTION RECOGNITION USING DEEP LEARNING." International Journal of Advance Research and Innovative Ideas In Education, vol. 8, no. 3, 2022, pp. 1921-1925.

IEEE Style

Vandana Singh, "SPEECH EMOTION RECOGNITION USING DEEP LEARNING," International Journal of Advance Research and Innovative Ideas In Education, vol. 8, no. 3, pp. 1921-1925, 2022.

Vancouver Style

Singh Vandana. SPEECH EMOTION RECOGNITION USING DEEP LEARNING. International Journal of Advance Research and Innovative Ideas In Education. 2022;8(3):1921-1925.

Harvard Style

Singh, Vandana (2022) 'SPEECH EMOTION RECOGNITION USING DEEP LEARNING', International Journal of Advance Research and Innovative Ideas In Education, 8(3), pp. 1921-1925.

Chicago Style

Singh, Vandana. "SPEECH EMOTION RECOGNITION USING DEEP LEARNING." International Journal of Advance Research and Innovative Ideas In Education 8, no. 3 (2022): 1921-1925.

Turabian Style

Singh, Vandana. "SPEECH EMOTION RECOGNITION USING DEEP LEARNING." International Journal of Advance Research and Innovative Ideas In Education 8, no. 3 (2022): 1921-1925.