The Efficacy of Deep Learning-Based Mixed Model for Speech Emotion Recognition

Human speech indirectly represents the mental state or emotion of others. The use of Artificial Intelligence (AI)-based techniques may bring revolution in this modern era by recognizing emotion from speech. In this study, we introduced a robust method for emotion recognition from human speech using...

Full description

Bibliographic Details
Main Authors: Uddin, Mohammad Amaz, Chowdury, Mohammad Salah Uddin, Khandaker, Mayeen Uddin *, Tamam, Nissren, Sulieman, Abdelmoneim
Format: Article
Language:English
Published: Tech Science Press 2022
Subjects:
Online Access:http://eprints.sunway.edu.my/2250/
http://eprints.sunway.edu.my/2250/1/28.pdf
_version_ 1848802237769318400
author Uddin, Mohammad Amaz
Chowdury, Mohammad Salah Uddin
Khandaker, Mayeen Uddin *
Tamam, Nissren
Sulieman, Abdelmoneim
author_facet Uddin, Mohammad Amaz
Chowdury, Mohammad Salah Uddin
Khandaker, Mayeen Uddin *
Tamam, Nissren
Sulieman, Abdelmoneim
author_sort Uddin, Mohammad Amaz
building SU Institutional Repository
collection Online Access
description Human speech indirectly represents the mental state or emotion of others. The use of Artificial Intelligence (AI)-based techniques may bring revolution in this modern era by recognizing emotion from speech. In this study, we introduced a robust method for emotion recognition from human speech using a well-performed preprocessing technique together with the deep learning-based mixed model consisting of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN). About 2800 audio files were extracted from the Toronto emotional speech set (TESS) database for this study. A high pass and Savitzky Golay Filter have been used to obtain noise-free as well as smooth audio data. A total of seven types of emotions; Angry, Disgust, Fear, Happy, Neutral, Pleasant-surprise, and Sad were used in this study. Energy, Fundamental frequency, and Mel Frequency Cepstral Coefficient (MFCC) have been used to extract the emotion features, and these features resulted in 97.5% accuracy in the mixed LSTM+CNN model. This mixed model is found to be performed better than the usual state-of-the-art models in emotion recognition from speech. It also indicates that this mixed model could be effectively utilized in advanced research dealing with sound processing.
first_indexed 2025-11-14T21:20:10Z
format Article
id sunway-2250
institution Sunway University
institution_category Local University
language English
last_indexed 2025-11-14T21:20:10Z
publishDate 2022
publisher Tech Science Press
recordtype eprints
repository_type Digital Repository
spelling sunway-22502023-06-16T01:38:32Z http://eprints.sunway.edu.my/2250/ The Efficacy of Deep Learning-Based Mixed Model for Speech Emotion Recognition Uddin, Mohammad Amaz Chowdury, Mohammad Salah Uddin Khandaker, Mayeen Uddin * Tamam, Nissren Sulieman, Abdelmoneim BF Psychology Q Science (General) TA Engineering (General). Civil engineering (General) Human speech indirectly represents the mental state or emotion of others. The use of Artificial Intelligence (AI)-based techniques may bring revolution in this modern era by recognizing emotion from speech. In this study, we introduced a robust method for emotion recognition from human speech using a well-performed preprocessing technique together with the deep learning-based mixed model consisting of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN). About 2800 audio files were extracted from the Toronto emotional speech set (TESS) database for this study. A high pass and Savitzky Golay Filter have been used to obtain noise-free as well as smooth audio data. A total of seven types of emotions; Angry, Disgust, Fear, Happy, Neutral, Pleasant-surprise, and Sad were used in this study. Energy, Fundamental frequency, and Mel Frequency Cepstral Coefficient (MFCC) have been used to extract the emotion features, and these features resulted in 97.5% accuracy in the mixed LSTM+CNN model. This mixed model is found to be performed better than the usual state-of-the-art models in emotion recognition from speech. It also indicates that this mixed model could be effectively utilized in advanced research dealing with sound processing. Tech Science Press 2022-09-22 Article PeerReviewed text en cc_by_4 http://eprints.sunway.edu.my/2250/1/28.pdf Uddin, Mohammad Amaz and Chowdury, Mohammad Salah Uddin and Khandaker, Mayeen Uddin * and Tamam, Nissren and Sulieman, Abdelmoneim (2022) The Efficacy of Deep Learning-Based Mixed Model for Speech Emotion Recognition. Computers, Materials & Continua, 74 (1). pp. 1709-1722. ISSN 1546-2226 https://doi.org/10.32604/cmc.2023.031177 10.32604/cmc.2023.031177
spellingShingle BF Psychology
Q Science (General)
TA Engineering (General). Civil engineering (General)
Uddin, Mohammad Amaz
Chowdury, Mohammad Salah Uddin
Khandaker, Mayeen Uddin *
Tamam, Nissren
Sulieman, Abdelmoneim
The Efficacy of Deep Learning-Based Mixed Model for Speech Emotion Recognition
title The Efficacy of Deep Learning-Based Mixed Model for Speech Emotion Recognition
title_full The Efficacy of Deep Learning-Based Mixed Model for Speech Emotion Recognition
title_fullStr The Efficacy of Deep Learning-Based Mixed Model for Speech Emotion Recognition
title_full_unstemmed The Efficacy of Deep Learning-Based Mixed Model for Speech Emotion Recognition
title_short The Efficacy of Deep Learning-Based Mixed Model for Speech Emotion Recognition
title_sort efficacy of deep learning-based mixed model for speech emotion recognition
topic BF Psychology
Q Science (General)
TA Engineering (General). Civil engineering (General)
url http://eprints.sunway.edu.my/2250/
http://eprints.sunway.edu.my/2250/
http://eprints.sunway.edu.my/2250/
http://eprints.sunway.edu.my/2250/1/28.pdf