Voice Feature Extraction for Gender and Emotion Recognition

Voice recognition plays a key function in spoken communication that facilitates identifying the emotions of person reflects within voice. Gender classification through speech is popular Human Computer Interaction (HCI) method on account determining gender computer hard. This led to development model for "Voice feature extraction Emotion and Recognition". The signal consists semantic information, speaker information (gender, age, emotional state), accompanied by noise. Females males have specific vocal traits because their acoustical perceptual variations along with variety which bring own perceptions. In order explore this area, requires pre-processing data, necessary increasing accuracy. proposed follows steps such as data extraction, using Activity Detector(VAD), Mel-Frequency Cepstral Coefficient(MFCC), reduction Principal Component Analysis(PCA) Support Vector Machine (SVM) classifier. combination techniques produced better results can be useful healthcare sector, virtual assistants, security purposes other fields related domain.