Abstract: This paper proposes an approach to recognise Assamese speaking person using Artificial Neural Network Model. Speaker recognition is the process of Identification of the person who is speaking depending on the characteristics of his/her voices. The features Linear Predictive Coding (LPC), Mel-Frequency Cepstral Coefficient (MFCC) are used to create the feature vector of the Assamese speech samples (words). Our database consists of ten speakers with equal number of male and female speakers where each word is uttered by twenty times by each speaker. The system contains the training phase, testing phase and recognition phase.

Keywords: Speaker Recognition, LPC, MFCC, Neural Network