Personified Emotion Detection from Speech using Supervised Machine Learning

Speech-based emotion recognition in machine learning is an emerging topic. In our daily routine, whatever speech we communicate can be based on our mood or emotion that we intend to share. In our model we have tried to categorize different emotions into specific class such as happiness, sadness, anger, calm, surprise, disgust, neutral and fear. The model uses the feature extraction techniques to collect different features which will be helpful to classify into different classes. Machine learning algorithms such as SVM, KNN are applied to classify the emotions of a person in real-time. The proposed system has the potential to be used in various applications such as mental health monitoring, human-robot interaction and speech therapy. The experimental results demonstrate that the proposed system achieves high accuracy in recognizing emotions from speech signals. The system’s performance can be further improved by using larger datasets, more advanced feature extraction methods, and deep learning algorithms. Overall, the proposed system has significant potential to recognise the human emotions for the well beings of an individual.