Framework for gender recognition using voice

In this article a SVM model with PCA has been used to recognize gender using voice of the person. A small dataset is used for training and testing the model. The records used have almost even distribution of genders all across. The proposed system is targeting the gender recognition in order to support the existing systems by reducing their search spaces intern reducing the delay in responses. The proposed model is a hybrid of Principal component analysis and SVM classifier, we show that this hybrid performs better than individual classifier. The system uses various acoustic parameter for the identification. The proposed model has achieved an accuracy of 98.42% during validation with good precision and recall. The duration of the audio signal is small for easier identification of words.