Age Based Cataloguing of Female Speakers Using A Naive Bayes Classifier

The age of speaker is a vital ingredient for many applications. Applications where access is based on age group can automatically use this simple system to identify the same. Access to machine or any equipment can also be authenticated with this system. Although there exist many difficulties when working with voice, it is a rich source of abundant information within it. With the help of acoustic and prosodic correlates of speech a model is developed in this research work to catalogue the voices into three different age groups. The MIT female prosodic database with 7 different data encoded in wav file format was used for testing. A Naive Bayes classifier was employed to do the classification into the three groups respectively. The classifier has worked on seven features extracted from the raw voice files and yielded 78.57% accuracy for classification. It is quite an interesting fact that voice embeds the age of a person and a proof can be given for the same.