A Novel BPNN Approach For Speaker Identification Using MFCC

Speech processing is an application area of digital signal processing.Various fields for research in speech processing are speech recognition, speaker recognition, speech synthesis, speech coding etc. The objective of speaker identification is to extract, characterize and identify the information about speaker identity. Feature extraction is the first step for speaker identification.In this work, the MFCC feature has been used for designing a text dependent speaker identification system.BPNN is used for identification after training the feature sets from MFCC.Some modifications to the existing techniques are also suggested to improve the speaker identification efficiency. Information from speech recognition can be used in various ways in state-of-the-art speaker identification systems.

Autorentext

The author Kshamamayee Dash is an Masters in engineering from Utkal University, India. After completing her B.tech in 2010 she has been doing extensive reserach in speech processing and has also won many acclamations for her work. She has published many research papers in speaker identification and is also continuing her research on speech.