基于实时语音转换的语音伪装通信系统

Y. Li, Tong Nie, Tian Yang, Zesheng Zhu, Yingying Xu, Shengnan Zhang, Yucheng Shao, Yusheng Jiang
{"title":"基于实时语音转换的语音伪装通信系统","authors":"Y. Li, Tong Nie, Tian Yang, Zesheng Zhu, Yingying Xu, Shengnan Zhang, Yucheng Shao, Yusheng Jiang","doi":"10.1109/ICCCS57501.2023.10151253","DOIUrl":null,"url":null,"abstract":"A Voice disguise communication (VDC) system is a system that disguises the voice in transmission and restores it at the receiving end. VDC systems have great application prospects in the field of confidential communication. The use of voice conversion (VC) can enhance the quality of voice disguise and reduce the recognition rate of eavesdroppers or automatic speaker verification (ASV) systems as a way to hide the identity of the speaker. There are three main constraints in applying VC to voice disguise at present: first, the real-time VC is poor and cannot meet the needs of real-time communication; second, the quality of voice disguise is not high, which is easily recognized by eavesdroppers or ASV systems; third, the corpus used for training is large, which poses certain difficulties and costs for implementation. Based on the above problems this research proposed a real-time VC method trained by a small corpus, and used it to design and implement a VDC system, and verified the effectiveness through experiments.","PeriodicalId":266168,"journal":{"name":"2023 8th International Conference on Computer and Communication Systems (ICCCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Voice Disguise Communication System Based on Real-Time Voice Conversion\",\"authors\":\"Y. Li, Tong Nie, Tian Yang, Zesheng Zhu, Yingying Xu, Shengnan Zhang, Yucheng Shao, Yusheng Jiang\",\"doi\":\"10.1109/ICCCS57501.2023.10151253\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A Voice disguise communication (VDC) system is a system that disguises the voice in transmission and restores it at the receiving end. VDC systems have great application prospects in the field of confidential communication. The use of voice conversion (VC) can enhance the quality of voice disguise and reduce the recognition rate of eavesdroppers or automatic speaker verification (ASV) systems as a way to hide the identity of the speaker. There are three main constraints in applying VC to voice disguise at present: first, the real-time VC is poor and cannot meet the needs of real-time communication; second, the quality of voice disguise is not high, which is easily recognized by eavesdroppers or ASV systems; third, the corpus used for training is large, which poses certain difficulties and costs for implementation. Based on the above problems this research proposed a real-time VC method trained by a small corpus, and used it to design and implement a VDC system, and verified the effectiveness through experiments.\",\"PeriodicalId\":266168,\"journal\":{\"name\":\"2023 8th International Conference on Computer and Communication Systems (ICCCS)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-04-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 8th International Conference on Computer and Communication Systems (ICCCS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCCS57501.2023.10151253\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 8th International Conference on Computer and Communication Systems (ICCCS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCCS57501.2023.10151253","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

语音伪装通信VDC (Voice disguise communication)系统是一种在传输过程中对语音进行伪装,并在接收端将其还原的系统。直流输电系统在保密通信领域具有广阔的应用前景。使用语音转换(VC)可以提高语音伪装的质量,降低窃听者或自动说话人验证(ASV)系统的识别率,作为隐藏说话人身份的一种方式。目前将VC应用于语音伪装主要存在三个制约因素:一是实时性差,不能满足实时通信的需要;二是语音伪装质量不高,容易被窃听者或ASV系统识别;第三,用于培训的语料库很大,这给实施带来了一定的困难和成本。基于以上问题,本研究提出了一种基于小语料库训练的实时VC方法,并利用该方法设计和实现了一个VDC系统,并通过实验验证了该方法的有效性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Voice Disguise Communication System Based on Real-Time Voice Conversion
A Voice disguise communication (VDC) system is a system that disguises the voice in transmission and restores it at the receiving end. VDC systems have great application prospects in the field of confidential communication. The use of voice conversion (VC) can enhance the quality of voice disguise and reduce the recognition rate of eavesdroppers or automatic speaker verification (ASV) systems as a way to hide the identity of the speaker. There are three main constraints in applying VC to voice disguise at present: first, the real-time VC is poor and cannot meet the needs of real-time communication; second, the quality of voice disguise is not high, which is easily recognized by eavesdroppers or ASV systems; third, the corpus used for training is large, which poses certain difficulties and costs for implementation. Based on the above problems this research proposed a real-time VC method trained by a small corpus, and used it to design and implement a VDC system, and verified the effectiveness through experiments.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信