Enhancing Work Safety Systems Through Real-Time Speech Emotion Detection Classifier Using CNN Algorithm

Speech emotion detection has emerged as a significant research area due to its potential applications in various domains. In work safety systems, the ability to accurately recognize emotions can provide vital information about the mental state of workers, which can be utilized to prevent work accidents and ensure a safer work environment. The objective of this study is to develop a speech emotion detection classifier using the CNN algorithm. The classifier aims to accurately classify emotions from speech signals, enabling real-time recognition of workers' emotional states. By achieving this objective, the study aims to contribute to the enhancement of work safety systems. The proposed methodology involves training a Convolutional Neural Network (CNN) model using a comprehensive dataset of labeled speech samples. The dataset will encompass various emotions, including happiness, sadness, anger, and fear. The CNN model will be trained to extract relevant features from speech signals and learn the patterns associated with different emotional states. Preprocessing techniques, such as audio segmentation, feature extraction, and data augmentation, will be employed to enhance the training process. The expected result of this study is a robust speech emotion detection classifier that can accurately classify emotions from speech signals. The classifier will be capable of real-time emotion recognition, providing immediate insights into workers' emotional states. By integrating this classifier into work safety systems, proactive measures can be taken to prevent work accidents based on workers' emotional conditions.