Speech Processing : Using Mel Frequency Cepstral Coefficients ( Mfcc )

1936 Words Nov 30th, 2014 8 Pages
Speaker reognition using Mel Frequency Cepstral Coefficients(MFCC)

Abstract Speech processing has emerged as one of the most important application area of digital signal processing. Various fields for research in speech processing are speech recognition, speaker recognition, speech analysis, speech synthesis, speech coding etc. The objective of automatic speaker recognition is to extract, characterize the discriminant features and recognize the information about speaker identity. In this paper we present a voice recognition system based on Mel Frequency Cepstral Coefficients (MFCC) and vector Quantization (VQ). This technique has an advantage that it creates fingerprint of human voice by exploiting human acoustic system and cepstral analysis. MFCC is widely accepted as a baseline for voice recognition due to these unique features.

KeywordsMFCC, Vector Quantization, Speaker recognition, Feature extraction, Fast Fourier Transform

Introduction
Human speech is the most natural form of communication and conveys both meaning and identity. The identity of a speaker can be determined from the information contained in the speech signal through speaker identification. Speaker identification is concerned with identifying unknown speakers from a database of speaker models previously enrolled in the system. Speaker (voice) identification has varied applications ranging from opening doors to security systems.
Speech processing is widely divided into 5 different…
Open Document