News

 Statistics

Number of Journals34
Number of Issues1,306
Number of Articles9,428
Article View9,191,889
PDF Download5,622,558
khalilpour, J., zarezadeh, E. (2018). Presenting A New Algorithm Based on GMM-UBM With Cochlear Filter- PNCC Feature for Speaker Verification. Electronic and Cyber Defense, 9(4), 441-448.
jafar khalilpour; Esmail zarezadeh. "Presenting A New Algorithm Based on GMM-UBM With Cochlear Filter- PNCC Feature for Speaker Verification". Electronic and Cyber Defense, 9, 4, 2018, 441-448.
khalilpour, J., zarezadeh, E. (2018). 'Presenting A New Algorithm Based on GMM-UBM With Cochlear Filter- PNCC Feature for Speaker Verification', Electronic and Cyber Defense, 9(4), pp. 441-448.
khalilpour, J., zarezadeh, E. Presenting A New Algorithm Based on GMM-UBM With Cochlear Filter- PNCC Feature for Speaker Verification. Electronic and Cyber Defense, 2018; 9(4): 441-448.

Presenting A New Algorithm Based on GMM-UBM With Cochlear Filter- PNCC Feature for Speaker Verification

علوم و فناوریهای پدافند نوین
Article 6, Volume 9, Issue 4 - Serial Number 34, August 2018, Pages 441-448    PDF (1.19 M)
Authors
jafar khalilpour* ; Esmail zarezadeh
Receive Date: 30 January 2019,  Revise Date: 17 July 2025,  Accept Date: 30 January 2019 
Abstract
In this paper, an auditory-inspired feature extraction algorithm based on a recently published time-frequency transform, i.e., auditory transform (AT) and the power normalized cepstral coefficients (PNCC) is proposed. Usually, the performance of acoustic models trained in clean speech drops significantly when tested on noisy speech.The proposed feature, called Cochlear Filter PNCC (CFPNCC), has shown strong robustness in the acoustic mismatch situations. An important feature of the proposed algorithm is the combination of advantages of the cochlear filter with the advantages of the PNCC feature, which has the resistance to both stationary noise and non-stationary noise. As shown in our experiments, in a GMM-UBM speaker verification system, CFPNCC outperforms the original PNCC and achieves the best overall results on the SSC database compared to the conventional features such as MFCC and RASTA-PLP under noisy conditions.
Keywords
peaker Verification; Feature Extraction; Noise Robustness
Statistics
Article View: 562
PDF Download: 288