DWT-MFCC Method for Speaker Recognition System with Noise

Fetty Amelia, Dadang Gunawan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The Mel-frequency Cepstral Coefficients (MFCC) method is the most popular method and has good performance as a feature extraction to date. But based on the simulation results, it is known that the speaker recognition system that uses MFCC as a feature extraction has low accuracy when applied to voice containing noise. So in this study, we propose the DWT-MFCC method to overcome this problem. The simulation results show that the DWT-MFCC method has higher accuracy compare with conventinal MFCC method when applied as feature extraction in the speaker recognition system with SNR from 15 to 40 dB.

Original languageEnglish
Title of host publication2019 7th International Conference on Smart Computing and Communications, ICSCC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728115573
DOIs
Publication statusPublished - 1 Jun 2019
Event7th International Conference on Smart Computing and Communications, ICSCC 2019 - Miri, Malaysia
Duration: 28 Jun 201930 Jun 2019

Publication series

Name2019 7th International Conference on Smart Computing and Communications, ICSCC 2019

Conference

Conference7th International Conference on Smart Computing and Communications, ICSCC 2019
CountryMalaysia
CityMiri
Period28/06/1930/06/19

    Fingerprint

Keywords

  • biometric
  • feature extraction
  • MFCC
  • Speaker recognition
  • wavelet

Cite this

Amelia, F., & Gunawan, D. (2019). DWT-MFCC Method for Speaker Recognition System with Noise. In 2019 7th International Conference on Smart Computing and Communications, ICSCC 2019 [8843660] (2019 7th International Conference on Smart Computing and Communications, ICSCC 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSCC.2019.8843660