Emotion Recognition Using Bayesian Learning from a Multi-Label Data Corpus


Swathi, Bandi and Kumar, Madapuri Rudra and Riyaz Belgaum, Mohammad and Alansari, Zainab (2022) Emotion Recognition Using Bayesian Learning from a Multi-Label Data Corpus. In: 2022 International Conference on Computing, Networking, Telecommunications & Engineering Sciences Applications (CoNTESA), 15-16 Dec 2022, Skopje, North Macedonia.

[img] Text
Emotion_Recognition.pdf - Published Version
Restricted to Repository staff only

Download (1MB)


In the digital era of information systems, emotion detection from audio signals is crucial for forensic services and operator or driver emotion monitoring in large-scale companies’ safety and security. Speech is a uniquely human trait used to express and communicate one’s point of view to others. Emotion recognition from speech audio signals is obtaining a presenter’s emotions from the presenter’s audio signal. Machine learning is used to develop emotion recognition systems, a critical research goal in current engineering research. The three main stages in speech emotion recognition are extraction of features, feature engineering, and classification. Even though powerful machine learning-based emotion identification algorithms for speech audio signals exist, the detection rate with maximum specificity and sensitivity is not scalable using most modern methods. A significant research objective is feature optimization for emotion recognition from speech audio signals. This article introduced a unique technique called Supervised Bayes Learning on Digital Features (SBL-DF). To scale its performance, the trials compared the suggested approach’s performance to an earlier model depicted against a similar goal. Experiment results indicate that the proposed method for optimizing features could be used on a large scale. The reference classifiers’ performance in making accurate detections with few false positives.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Hidden Markov methods, artificial neural networks, genetic Algorithms, artificial intelligence, and speech technology
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines
Divisions: Faculty of Computing and Informatics (FCI)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 09 Mar 2023 01:33
Last Modified: 09 Mar 2023 01:33
URII: http://shdl.mmu.edu.my/id/eprint/11215


Downloads per month over past year

View ItemEdit (login required)