基于混合分類(lèi)器的AMR-WB語(yǔ)音隱寫(xiě)分析方法
發(fā)布時(shí)間:2021-12-16 19:41
基于自適應(yīng)多速率寬帶語(yǔ)音編碼的信息隱藏方法具有較強(qiáng)的隱蔽性和抗檢測(cè)能力。為檢測(cè)導(dǎo)譜頻率矢量索引搜索中的量化索引調(diào)制,提出了一種基于校準(zhǔn)技術(shù)和混合分類(lèi)器的隱寫(xiě)分析方法。其中,一種基于長(zhǎng)短期記憶模型的特征提取方法被用于提取導(dǎo)譜頻率的關(guān)聯(lián)性特征,導(dǎo)譜頻率量化索引的概率分布則作為導(dǎo)譜頻率的長(zhǎng)時(shí)分布特征。以上兩種特征通過(guò)校準(zhǔn)技術(shù)處理后,被送入支持向量機(jī)中進(jìn)行訓(xùn)練,可獲得具有較高分類(lèi)性能的分類(lèi)器。實(shí)驗(yàn)結(jié)果表明,在不同嵌入率和語(yǔ)音長(zhǎng)度下,所提方法均有較高的分類(lèi)正確率。
【文章來(lái)源】:通信技術(shù). 2020,53(10)
【文章頁(yè)數(shù)】:7 頁(yè)
【參考文獻(xiàn)】:
期刊論文
[1]Steganography in low bit-rate speech streams based on quantization index modulation controlled by keys[J]. HUANG YongFeng,TAO HuaiZhou,XIAO Bo,CHANG ChinChen. Science China(Technological Sciences). 2017(10)
[2]Detection of quantization index modulation steganography in G.723.1 bit stream based on quantization index sequence analysis[J]. Song-bin LI 1,2,Huai-zhou TAO1,2,Yong-feng HUANG 1,2(1Department of Electronic Engineering,Tsinghua University,Beijing 100084,China)(2Tsinghua National Laboratory for Information Science and Technology,Beijing 100084,China). Journal of Zhejiang University-Science C(Computers & Electronics). 2012(08)
本文編號(hào):3538717
【文章來(lái)源】:通信技術(shù). 2020,53(10)
【文章頁(yè)數(shù)】:7 頁(yè)
【參考文獻(xiàn)】:
期刊論文
[1]Steganography in low bit-rate speech streams based on quantization index modulation controlled by keys[J]. HUANG YongFeng,TAO HuaiZhou,XIAO Bo,CHANG ChinChen. Science China(Technological Sciences). 2017(10)
[2]Detection of quantization index modulation steganography in G.723.1 bit stream based on quantization index sequence analysis[J]. Song-bin LI 1,2,Huai-zhou TAO1,2,Yong-feng HUANG 1,2(1Department of Electronic Engineering,Tsinghua University,Beijing 100084,China)(2Tsinghua National Laboratory for Information Science and Technology,Beijing 100084,China). Journal of Zhejiang University-Science C(Computers & Electronics). 2012(08)
本文編號(hào):3538717
本文鏈接:http://www.sikaile.net/kejilunwen/wltx/3538717.html
最近更新
教材專(zhuān)著