This paper presents a study of how speech features have comparable parameters amongst blood relations. Mel Frequency Cepstral Coefficients (MFCC) has been used for extracting the features of input speech signal, along with vector quantization through modified k-means LBG (Linde, Buzo, and Gray) algorithm are implemented to analyse and estimate the similarity to perform related studies. The study is concentrated on database using 12 families from which voice databases were collected from all users, of different age groups, of each family. The Finding of the study shows a high correlation (Max 95%) between similar genders of the family and low correlation (Min 80%) between dissimilar genders of the family.
P. Padmini, Tripathi, S., and Dr. Kaustav Bhowmick, “Identification of correlation between blood relations using speech signal”, in 2017 IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems (SPICES), 2017.