A playback speech detection algorithm based on log inverse Mel-frequency spectral coefficient

The popularity and portability of high-fidelity audio recording equipment and playback equipment poses a serious challenge for speaker recognition systems against playback attacks.Based on the differences between the original speech and the playback speech in high frequency region,the algorithm reve...

Full description

Saved in:
Bibliographic Details
Main Authors: Lang LIN, Rangding WANG, Diqun YAN, Can LI
Format: Article
Language:zho
Published: Beijing Xintong Media Co., Ltd 2018-05-01
Series:Dianxin kexue
Subjects:
Online Access:http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2018020/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841529122598158336
author Lang LIN
Rangding WANG
Diqun YAN
Can LI
author_facet Lang LIN
Rangding WANG
Diqun YAN
Can LI
author_sort Lang LIN
collection DOAJ
description The popularity and portability of high-fidelity audio recording equipment and playback equipment poses a serious challenge for speaker recognition systems against playback attacks.Based on the differences between the original speech and the playback speech in high frequency region,the algorithm reversed the Mel-filter bank in Mel-frequency cepstral coefficient (MFCC) calculation,and the coefficients before the DCT were used as the features of the algorithm.SVM was utilized as the classifier.Experimental results show that this algorithm can effectively detect the playback speech.In addition,the algorithm is integrated into the GMM-UBM speaker recognition system,which significantly improves the systems’ capability of resisting the playback attack.
format Article
id doaj-art-c26f476a2ac8483d924c499382cd9d17
institution Kabale University
issn 1000-0801
language zho
publishDate 2018-05-01
publisher Beijing Xintong Media Co., Ltd
record_format Article
series Dianxin kexue
spelling doaj-art-c26f476a2ac8483d924c499382cd9d172025-01-15T03:25:19ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012018-05-0134909859801888A playback speech detection algorithm based on log inverse Mel-frequency spectral coefficientLang LINRangding WANGDiqun YANCan LIThe popularity and portability of high-fidelity audio recording equipment and playback equipment poses a serious challenge for speaker recognition systems against playback attacks.Based on the differences between the original speech and the playback speech in high frequency region,the algorithm reversed the Mel-filter bank in Mel-frequency cepstral coefficient (MFCC) calculation,and the coefficients before the DCT were used as the features of the algorithm.SVM was utilized as the classifier.Experimental results show that this algorithm can effectively detect the playback speech.In addition,the algorithm is integrated into the GMM-UBM speaker recognition system,which significantly improves the systems’ capability of resisting the playback attack.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2018020/speaker recognitionplayback speech detectionlog Mel-frequency spectruminverse Mel-filter group
spellingShingle Lang LIN
Rangding WANG
Diqun YAN
Can LI
A playback speech detection algorithm based on log inverse Mel-frequency spectral coefficient
Dianxin kexue
speaker recognition
playback speech detection
log Mel-frequency spectrum
inverse Mel-filter group
title A playback speech detection algorithm based on log inverse Mel-frequency spectral coefficient
title_full A playback speech detection algorithm based on log inverse Mel-frequency spectral coefficient
title_fullStr A playback speech detection algorithm based on log inverse Mel-frequency spectral coefficient
title_full_unstemmed A playback speech detection algorithm based on log inverse Mel-frequency spectral coefficient
title_short A playback speech detection algorithm based on log inverse Mel-frequency spectral coefficient
title_sort playback speech detection algorithm based on log inverse mel frequency spectral coefficient
topic speaker recognition
playback speech detection
log Mel-frequency spectrum
inverse Mel-filter group
url http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2018020/
work_keys_str_mv AT langlin aplaybackspeechdetectionalgorithmbasedonloginversemelfrequencyspectralcoefficient
AT rangdingwang aplaybackspeechdetectionalgorithmbasedonloginversemelfrequencyspectralcoefficient
AT diqunyan aplaybackspeechdetectionalgorithmbasedonloginversemelfrequencyspectralcoefficient
AT canli aplaybackspeechdetectionalgorithmbasedonloginversemelfrequencyspectralcoefficient
AT langlin playbackspeechdetectionalgorithmbasedonloginversemelfrequencyspectralcoefficient
AT rangdingwang playbackspeechdetectionalgorithmbasedonloginversemelfrequencyspectralcoefficient
AT diqunyan playbackspeechdetectionalgorithmbasedonloginversemelfrequencyspectralcoefficient
AT canli playbackspeechdetectionalgorithmbasedonloginversemelfrequencyspectralcoefficient