Emotion Detection and Gender Identification Using Audio Signals

Emotion is often defined as a complex state of feeling that results in physical and psychological changes that influence thought and behaviour. Emotion modelling and recognition has drawn extensive attention from disciplines such as psychology, cognitive science and engineering. The main goal is to identify the emotional or physical state of a human being from his or her voice. A speaker has dissimilar stages throughout speech that are recognized as emotional aspects of speech and are integrated in the so named paralinguistic aspects. The database considered for emotion recognition is based on audio signals. Fundamental frequency plays a vital role in Gender identification. Based on empirical mode decomposition method detect the dynamically evolving emotion patterns. Classification features are based on the instantaneous frequency and the local oscillation within every mode. The proposed system uses the pre-processing filters to remove the noise and therefore the emotional states were identified efficiently.