Spoofing speech detection algorithm based on joint feature and random forest

In order to describe the characteristic information of the speech signal more comprehensively and improve the detection rate of camouflage, a spoofing speech detection method based on the combination of uniform local binary pattern texture feature and constant Q cepstrum coefficient acoustic feature...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiaqi YU, Zhihua JIAN, Jia XU, Lin YOU, Yunlu WANG, Chao WU
Format: Article
Language:zho
Published: Beijing Xintong Media Co., Ltd 2022-06-01
Series:Dianxin kexue
Subjects:
Online Access:http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2022089/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850031303108329472
author Jiaqi YU
Zhihua JIAN
Jia XU
Lin YOU
Yunlu WANG
Chao WU
author_facet Jiaqi YU
Zhihua JIAN
Jia XU
Lin YOU
Yunlu WANG
Chao WU
author_sort Jiaqi YU
collection DOAJ
description In order to describe the characteristic information of the speech signal more comprehensively and improve the detection rate of camouflage, a spoofing speech detection method based on the combination of uniform local binary pattern texture feature and constant Q cepstrum coefficient acoustic feature was proposed, which used random forest as the classifier model.The texture feature vector in the speech signal spectrogram was extracted by using the uniform local binary mode, and the joint feature was formed with the constant Q cepstrum coefficient.Then, the obtained joint feature vector was used to train the random forest classifier, so as to realize the camouflage speech detection.In the experiment, the performances of several spoofing detection systems constructed by other feature parameters and the support vector machine classifier model were compared, and the results show that the proposed speech spoofing detection system combined with the joint feature and the random forest model has the best performance.
format Article
id doaj-art-dc43b120b5d14a5c8122663668e1c535
institution DOAJ
issn 1000-0801
language zho
publishDate 2022-06-01
publisher Beijing Xintong Media Co., Ltd
record_format Article
series Dianxin kexue
spelling doaj-art-dc43b120b5d14a5c8122663668e1c5352025-08-20T02:59:00ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012022-06-0138919959811292Spoofing speech detection algorithm based on joint feature and random forestJiaqi YUZhihua JIANJia XULin YOUYunlu WANGChao WUIn order to describe the characteristic information of the speech signal more comprehensively and improve the detection rate of camouflage, a spoofing speech detection method based on the combination of uniform local binary pattern texture feature and constant Q cepstrum coefficient acoustic feature was proposed, which used random forest as the classifier model.The texture feature vector in the speech signal spectrogram was extracted by using the uniform local binary mode, and the joint feature was formed with the constant Q cepstrum coefficient.Then, the obtained joint feature vector was used to train the random forest classifier, so as to realize the camouflage speech detection.In the experiment, the performances of several spoofing detection systems constructed by other feature parameters and the support vector machine classifier model were compared, and the results show that the proposed speech spoofing detection system combined with the joint feature and the random forest model has the best performance.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2022089/spoofing speech detectionacoustic featuretexture featureuniform local binary patternrandom forest
spellingShingle Jiaqi YU
Zhihua JIAN
Jia XU
Lin YOU
Yunlu WANG
Chao WU
Spoofing speech detection algorithm based on joint feature and random forest
Dianxin kexue
spoofing speech detection
acoustic feature
texture feature
uniform local binary pattern
random forest
title Spoofing speech detection algorithm based on joint feature and random forest
title_full Spoofing speech detection algorithm based on joint feature and random forest
title_fullStr Spoofing speech detection algorithm based on joint feature and random forest
title_full_unstemmed Spoofing speech detection algorithm based on joint feature and random forest
title_short Spoofing speech detection algorithm based on joint feature and random forest
title_sort spoofing speech detection algorithm based on joint feature and random forest
topic spoofing speech detection
acoustic feature
texture feature
uniform local binary pattern
random forest
url http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2022089/
work_keys_str_mv AT jiaqiyu spoofingspeechdetectionalgorithmbasedonjointfeatureandrandomforest
AT zhihuajian spoofingspeechdetectionalgorithmbasedonjointfeatureandrandomforest
AT jiaxu spoofingspeechdetectionalgorithmbasedonjointfeatureandrandomforest
AT linyou spoofingspeechdetectionalgorithmbasedonjointfeatureandrandomforest
AT yunluwang spoofingspeechdetectionalgorithmbasedonjointfeatureandrandomforest
AT chaowu spoofingspeechdetectionalgorithmbasedonjointfeatureandrandomforest