International Journal of Advanced Engineering Research and Science (IJAERS) Vol-3, Issue-5 , May- 2016] ISSN: 2349-6495 www.ijaers.com Page | 4 Voice Based Biometric System Feature Extraction Using MFCC and LPC Technique Mr. Vijay K. Kale 1 , Dr. Prapti D.Deshmukh 2 , Mr.Hanumant R.Gite 3 1,3 Department of Computer Science & IT, Dr.Babasaheb Ambedkar Marathwada University, Aurangabad, (MS), India 2 MGM’S Dr.G.Y.Pathrikar College of Computer Science & IT, Aurangabad, (MS), India Abstract— Now a day, interest in using biometric technologies for person authentication in security systems has grown rapidly.Voice is one of the most promising and mature biometric modalities for secured access control this paper gives an experimental overview of techniques used for feature extraction in speaker recognition. The research in speaker recognition have been evolved starting from short time features reflecting spectral properties of speech low-level or physical traits to the high level features (behavioral traits) such as prosody, phonetic information, conversational patterns etc. first give a brief overview of Speech processing and voice biometric relation and then describe some feature extraction technique. We have performed experiment for feature extraction of MFCC, LPC techniques. Keywords— MFCC, LPC, Biometric, Feature, Voice. I. INTRODUCTION Now a day in various field computerizations growing number of speaker-recognition tasks with such a technologies as speaker verification and speaker identification. Voice biometrics uses the features of a person’s voice to find out the speaker’s identity. Systems performing this function have been applied to real-world security applications for more than a decade. Their use is increasing rapidly in a broad spectrum of industries, including financial services, retail, corrections, even entertainment. Voice-biometrics systems can be categorized as belonging in two industries: speech processing and biometric security. Human voice conveys information about the language being spoken and the emotion and gender for the identity of the speaker. Speaker recognition is a process where a person is recognized on the basis of his voice signals [1, 2]. The Objective of speaker recognition is to determine which speaker is present based on the individual’s utterance. This is in contrast with speaker verification, where the objective is to verify the person’s claimed identity based On his or her utterance. Speaker identification and speaker verification fall under the general category of Speaker recognition [3, 4].In speaker identification there is two types, one is text dependent and another is text independent. Speaker identification is divided into two components: feature extraction and feature. Fig 1.1:Voice Biometric Tree Structure Historically, all speaker recognition systems have been mainly based on acoustic cues that are nothing but physical traits extracted from spectral characteristics of speech signals. So far the features derived from the speech spectrum have proven to be the most effective in automatic systems, because the spectrum reflects the geometry of system that generates the signal. Therefore the variability in the dimensions of the vocal track is reflected in the variability of the spectra between the speakers. However, studies [5] have proved that there is a large amount of information suitable for speaker recognition being the top part related to learned traits and the bottom part to physical traits. II. VOICE BIOMETRICS TYPES 1. Speaker verification: Speaker-verification systems authenticate that a person is who she or he claims to be. 2. Speaker Identification: Speaker identification Assigns an identity to the voice of an unknown speaker III. SPEECH RECOGNITION PROCESS The speaker Reorganization system may be viewed as working in a four stages • Analysis