Modified deep attractor neural networks for variability compensation in recognition tasks

Shaghayegh Reza,Seyyed Ali Seyyedsalehi,Seyyede Zohreh Seyyedsalehi

Computers and Electrical Engineering（2022）

引用 0|浏览2

暂无评分

摘要

•Variability compensation techniques are essential for robust recognition systems.•Denoising autoencoders can degrade variabilities in recognition tasks.•Modified deep attractor neural network compensates and recognizes simultaneously.•Variabilities are compensated by pulling samples to their corresponding attractors.

查看译文

关键词

Robust recognition,Denoising autoencoders,Deep attractor neural networks,Variability compensation

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要