Abstract
At present, Speaker recognition systems are being widely used in speaker detection, authentication and authorization to perform secure transactions in various personal, commercial and industrial applications. As speaker recognition in noisy environments is becoming increasingly difficult, a novel system is developed using MFCC and Vector Quantization. The training data is collected from 15 native speakers. LMS, NLMS and RLS adaptive filters are used to reduce the noise in the speech signal. The performance of all the speaker recognition systems is rated by calculating the Equal Error Rate (ERR) and Euclidian distance.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
