Never forget, Its Freedom Deal. Use IRE15 promo code and Get 150 INR / 2 USD discount on processing charges. Promo offer valid from 5th August 2020 to 25th August 2020.

Telephone Voice Speaker Recognition Using Mel Frequency Cepstral Coefficients With Cascaded Feed Forward Neural Network
  • Author(s): M. F. Franklin Nissy ; G. Renisha
  • Paper ID: 1701959
  • Page: 164-170
  • Published Date: 27-02-2020
  • Published In: Iconic Research And Engineering Journals
  • Publisher: IRE Journals
  • e-ISSN: 2456-8880
  • Volume/Issue: Volume 3 Issue 8 February-2020
Abstract

Speaker recognition is the process of identification of the person from the characteristics of his voice. It provides service such as database access services, information services and security control for confidential information areas. However, the accurateness of speaker recognition often drops off quickly because of the low-quality speech and sound. To overcome this problem a new speaker recognition model based on Mel frequency cepstral coefficients (MFCC) are used for feature extraction. Feature extraction means that the speech signal is converted into a series of feature vector coefficients. These features only include the information needed to identify the speaker and discarding all other stuff which carries information like background noise, emotion etc. Features extracted from MFCC are given as the input to the Cascaded Feed Forward Neural Network (CFFNN) which identifies the speech signal of the corresponding speaker. MFCC is an efficient way to extract features from the signal and the Mel scale based feature extraction gives better accuracy in the clean and noisy environment.

Keywords

Speaker recognition, Mel Frequency Cepstral Coefficients (MFCC), Cascaded Feed Forward Neural Network (CFFNN), Feed Forward Neural Network (FFNN)

Citations

IRE Journals:
M. F. Franklin Nissy , G. Renisha "Telephone Voice Speaker Recognition Using Mel Frequency Cepstral Coefficients With Cascaded Feed Forward Neural Network" Iconic Research And Engineering Journals Volume 3 Issue 8 2020 Page 164-170

IEEE:
M. F. Franklin Nissy , G. Renisha "Telephone Voice Speaker Recognition Using Mel Frequency Cepstral Coefficients With Cascaded Feed Forward Neural Network" Iconic Research And Engineering Journals, 3(8)