Integration of Variational Autoencoder and Spatial Clustering for Adaptive Multi-Channel Neural Speech Separation

Žmolíková, Kateřina; Delcroix, Marc; Burget, Lukáš; Nakatani, Tomohiro; Černocký, Jaň

doi:10.1109/slt48900.2021.9383612

Cited by 3 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this way, the features reconstructed by the autoencoder of standard samples and attack samples are synthesized to enrich the information of pieces y i . When the works belong to two different distributions, a sample y i marked as usual should be more similar to the representation of y n i than 2 , and vice versa. e goal in the autoencoder step is to exploit the influence of one channel on every other track in the supervised stage to greatly differentiate the difference between the two classes ordinary and attack.…”

Section: Architecture Of Multichannel Autoencoder Deep Learningmentioning

confidence: 99%

See 1 more Smart Citation

A Metaheuristic Autoencoder Deep Learning Model for Intrusion Detector System

Pandey

Kumar

Lamin

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

A multichannel autoencoder deep learning approach is developed to address the present intrusion detection systems’ detection accuracy and false alarm rate. First, two separate autoencoders are trained with average traffic and assault traffic. The original samples and the two additional feature vectors comprise a multichannel feature vector. Next, a one-dimensional convolution neural network (CNN) learns probable relationships across channels to better discriminate between ordinary and attack traffic. Unaided multichannel characteristic learning and supervised cross-channel characteristic dependency are used to develop an effective intrusion detection model. The scope of this research is that the method described in this study may significantly minimize false positives while also improving the detection accuracy of unknown attacks, which is the focus of this paper. This research was done in order to improve intrusion detection prediction performance. The autoencoder can successfully reduce the number of features while also allowing for easy integration with different neural networks; it can reduce the time it takes to train a model while also improving its detection accuracy. An evolutionary algorithm is utilized to discover the ideal topology set of the CNN model to maximize the hyperparameters and improve the network’s capacity to recognize interchannel dependencies. This paper is based on the multichannel autoencoder’s effectiveness; the fourth experiment is a comparative analysis, which proves the benefits of the approach in this article by correlating it to the findings of various different intrusion detection methods. This technique outperforms previous intrusion detection algorithms in several datasets and has superior forecast accuracy.

show abstract

Section: Architecture Of Multichannel Autoencoder Deep Learningmentioning

confidence: 99%

“…To do this, it needs to build a model that can tell the difference between an attack and normal network traffic. en, NIDS can turn intrusion detection into pattern recognition and classification, use the same kinds of algorithms to get data, clean it, model it, and classify different network behaviors [2].…”

Section: Introductionmentioning

confidence: 99%