Please use this identifier to cite or link to this item: https://hdl.handle.net/11147/2101
Title: Convolutional bias removal based on normalizing the filterbank spectral magnitude
Authors: Tüfekçi, Zekeriya
Keywords: Additive noise
Convolutional noise
Robust speaker verification
Convolution
Filter banks
Issue Date: Jul-2007
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source: Tüfekçi, Z. (2007). Convolutional bias removal based on normalizing the filterbank spectral magnitude. IEEE Signal Processing Letters, 14(7), 485-488. doi:10.1109/LSP.2006.891313
Abstract: In this letter, a novel convolutional bias removal technique is proposed. The proposed method is based on scaling the filterbank magnitude by the average of filterbank magnitude over time. The relation between the cepstral mean normalization (CMN) and proposed algorithm is derived. The experimental results show that the proposed algorithm is more robust than the CMN for both convolutional bias and additive noise. For example, the proposed method reduced the equal error rate by 5.66% and 10.16% on average for the convolutional bias and 12-dB additive noise, respectively.
URI: http://doi.org/10.1109/LSP.2006.891313
http://hdl.handle.net/11147/2101
ISSN: 1070-9908
1070-9908
Appears in Collections:Electrical - Electronic Engineering / Elektrik - Elektronik Mühendisliği
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Files in This Item:
File Description SizeFormat 
2101.pdfMakale134.39 kBAdobe PDFThumbnail
View/Open
Show full item record

CORE Recommender

SCOPUSTM   
Citations

7
checked on Dec 11, 2021

WEB OF SCIENCETM
Citations

6
checked on Jan 22, 2022

Page view(s)

38
checked on Jan 24, 2022

Download(s)

38
checked on Jan 24, 2022

Google ScholarTM

Check

Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.