Speech Emotion Recognition Using Support Vector Machine

Speech Emotion Recognition (SER) is a significant research field focusing on the automatic recognition and classification of emotions from speech signals. With the advancement of machine learning techniques, SER has seen significant development in recent years. This study presents a methodology for SER using a Support Vector Machine method. The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) dataset is used to evaluate the effectiveness of the proposed method, which includes seven emotional states: calmness, neutrality, furiousness, pleasure, fear, sadness, and disgust startlement. The results show that the Support Vector Machine method notably improves over the other machine learning models by providing the highest recognition accuracy of 85% on the RAVDESS dataset.