A Speech Emotion Recognition Model to Detect Aggressive Behavior in Dialogues

• Gabriel Gonçalves Ferreira Instituto Tecnológico de Aeronáutica http://orcid.org/0009-0002-2085-6159
• Johnny Marques Instituto Tecnológico de Aeronáutica https://orcid.org/0000-0002-1551-435X

DOI: https://doi.org/10.5753/sbsi_estendido.2024.238648

Resumo

Speech Emotion Recognition (SER) is a multidisciplinary field that involves the development of computational models to automatically detect and analyze emotional states conveyed through speech signals. Utilizing techniques from signal processing, machine learning, and natural language processing, SER systems extract relevant features from audio data and classify emotions into distinct categories such as happiness, sadness, anger, and more. This work aims to leverage the latest SER techniques to build a robust model that can detect aggressive behavior in dialogues solely based on audio input signals.

Palavras-chave: speech emotion recognition, artificial intelligence, machine learning, convolutional neural networks, support vector machines

Referências

Jolly, M., Gupta, P., Bansal, S., Gupta, G., and Goel, R. (2023). Machine learning based speech emotion recognition in hindi audio. In 2023 7th International Conference on Trends in Electronics and Informatics (ICOEI). IEEE.

Nahar, M. and Ali, M. E. (2022). A deep ensemble approach of anger detection from audio-textual conversations. In 2022 10th International Conference on Affective Computing and Intelligent Interaction (ACII). IEEE.

Padhy, S., Das, N., Tiwari, S., and Arora, S. (2022). AI based web app and framework for detecting emotions from human speech. In 2022 2nd Odisha International Conference on Electrical Power Engineering, Communication and Computing Technology (ODICON). IEEE.

Seknedy, M. E. and Fawzi, S. (2023). Arabic english speech emotion recognition system. In 2023 20th Learning and Technology Conference (L&T). IEEE.