...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Acta Infologica >?oklu Ortam Sistemleri ??in Siber Güvenlik Kapsam?nda Derin ??renme Kullanarak Ses Sahne ve Olaylar?n?n Tespiti
【24h】

?oklu Ortam Sistemleri ??in Siber Güvenlik Kapsam?nda Derin ??renme Kullanarak Ses Sahne ve Olaylar?n?n Tespiti

机译：？网络安全范围中的箭头媒体系统使用深度？

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

trenGünümüzde do?adaki bir?ok do?al ses kayna?? yan?s?ra sentetik sesler de ?oklu ortam sistemlerinde kullan?lmaktad?r. Bu seslerin bulundu?u ortamlar (sahneler) biyometrik yetkilendirme, güvenlik isterleri ve gürbüz/güvenli sesli/g?rüntülü ileti?im i?in ?nem arz etmektedir. Konu?ma/konu?mac? tan?ma, do?rulama gibi ?zel k?s?tlara sahip ses bi?emleri haricinde ?oklu seslerin ayr??t?r?lmas?, gürültü giderilmesi, ses sahnesi/ olaylar?n?n tespiti ve ses etiketleme i?lemleri siber güvenlik a??s?ndan daha güvenli bili?im sistemleri olu?turulmas? ad?na gün ge?tik?e ?nem kazanmaktad?r. Derin ??renme katmanl? altyap?s? gere?i olduk?a iyi bir bi?imde ham verideki ?zniteliklerin ve anlamsal ili?kinin elde edilmesine olanak sunmas?ndan dolay? son y?lllarda siber güvenlik alan?nda da tercih edilir olmu?tur. Bu ?al??mada siber güvenlik kapsam?nda ?oklu ortam verisi olarak ses (veya konu?ma) analizi ve s?n?fland?rma/tahminleme ve tespit i?in derin ??renme mimari modellerinin kullan?m? irdelenmi?tir. ?al??mam?zda 2015 ila 2019 y?llar? aras?ndaki yay?nlarda ?ne ??kan modeller olan derin sinir a?lar?, evri?imli sinir a?lar?, tekrarlay?c? sinir a?lar?, k?s?tlanm?? Boltzmann makinesi ve derin inan? a?lar? sistematik olarak incelenmi?tir. B?ylece siber güvenlikte ses/konu?ma i?leme, sesle aldatmay? ?nleme, tutarl? ve yüksek ba?ar?ml? sonu?lar? elde etmeye dair literatürdeki y?nelim k?rk? a?k?n ?al??ma üzerinden bilimsel bulgulara dayanan tart??ma ve yorumlarla a??k?a ortaya konulmaktad?r.In addition to many natural sound sources in nature, synthetic sounds are also used in the multimedia systems of our modern world. Environments (i.e., sound scenes) with these sounds are important for biometric authorization, security requirements and robust/safer voice/video communication. Apart from audio formats that have special constraints such as speech/speaker recognition and verification, the separation of polyphonic sounds, noise reduction, detection of sound scenes/events and voice tagging processes are gaining importance in order to create safer information systems in terms of cyber security. In recent years deep learning has been preferred in the field of cyber security due to its layered infrastructure, which enables the easy extraction of attributes and semantic relationships in the raw data. In this study, the use of deep learning architecture models for voice (or speech) analysis and classification/prediction and detection as multimedia data in cyber security coverage is examined. In our study, deep neural networks, convolutional neural networks, recurrent neural networks, restricted Boltzmann machine and deep belief networks are systematically reviewed as prominent models in the publications between 2015 and 2019. Therefore, the orientation in the literature on voice/speech processing in cyber security, prevention of voice spoofing, and achieving consistent and high performance results is clearly demonstrated through discussions and comments based on scientific findings over fourty studies.
机译：做吗？好吗？合成声音的合成声音？lmaktad？lma。这些声音（场景）的媒体（场景）是生物识别，安全性，无论是想要的和gürbüz/ secure / g吗？g？ex。主题？MA /主题？MAC？棕褐色，就像做？统治，语音BI？Zeals？检测箭头的音频声音，音频场景/事件？网络安全的网络安全比网络安全更安全？系统系统？调节？ na-day ge的名称ge？tik？e？e？湿度。深度？等级层？基础设施？S？ gere？我有一个很好的bi？在原始数据中的ime？zniates和语义省？允许它获得？它在去年的网络安全区域也是首选的。这是作为网络安全范围中的媒体数据的语音（或主题？MA）分析和SIA或主题）分析？•使用深色型架构模型？是坚持不懈的？ ？妈妈？ZDA 2015到2019年Y？在弓？ne？什么是深神经a？血液模型？神经a？s？s？tlanm ?? Boltzmann机器和深度相信？作为？系统地审查。 B？ylece网络安全声音/主题？ ？导航，金额？和高ba？ar？ml？结束？s？ Y？Nuri K？在文献中获得的rk？对科学发现的科学结果进行了科学发现的挞？r.in除了许多自然声源本质上，综合声音也用于我们现代世界的多媒体系统。具有这些声音的环境（即声音场景）对于生物识别，安全要求和强大/更安全语音/视频通信非常重要。除了具有语音/扬声器识别和验证之类的特殊约束的音频格式之外，多音声音的分离，降噪，声音场景/事件的检测和语音标记过程的重要性才能创建更安全的网络安全方案。近年来，由于其分层基础设施，网络安全领域一直是深入的学习，这使得能够轻松提取原始数据中的属性和语义关系。在这项研究中，检查了用于语音（或语音）分析和分类/预测和检测的深度学习架构模型作为网络安全覆盖中的多媒体数据。在我们的研究中，深度神经网络，卷积神经网络，经常性神经网络，限制的Boltzmann机器和深度信仰网络被系统地审查了2015年和2019年之间的出版物中的突出模型。因此，语音/语音处理网络中文献中的方向通过基于四十研究的科学结果的讨论和评论，清楚地证明了安全性，防止语音欺骗和实现一致和高性能结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号