Subspace techniques for task-independent EEG person identification
Citations
14 citations
4 citations
4 citations
4 citations
Cites background or methods or result from "Subspace techniques for task-indepe..."
...In [9], only preliminary results were discussed with no inter-task or inter-subject analysis....
[...]
...In [9], these subspace systems were modified to process information from multiple channels by concatenating channel-wise statistics at an intermediate processing level....
[...]
...i -vector and x-vector subspace context, the proposed modification in [9] is better than the direct early and late fusion techniques to model the data from different models....
[...]
...• This paper builds upon subspace systems introduced in [9] and proposes a novel system that combines the i -vector and the x-vector representations....
[...]
...systems proposed in [9] using two datasets....
[...]
3 citations
References
40,826 citations
"Subspace techniques for task-indepe..." refers methods in this paper
...LDA is computed over these embeddings, and a one-vs-all SVM classifier [15] is built using a cosine kernel to predict the person IDs....
[...]
...Finally, a one-vsall support vector machine (SVM) [15] with a cosine kernel is trained to predict the class labels....
[...]
4,673 citations
"Subspace techniques for task-indepe..." refers methods in this paper
...Universal background model-Gaussian mixture model (UBM-GMM) [9] systems have been widely used for EEG person identification [5], [10]–[13]....
[...]
...This configuration was fine-tuned for the UBM-GMM system in [5]....
[...]
...During testing, Top-C scoring is used to determine the identity of the EEG segment [9]....
[...]
3,526 citations
2,300 citations
"Subspace techniques for task-indepe..." refers background or methods in this paper
...Similarly, x-vector is a deep neural network (DNN) based speaker recognition approach proposed in [7]....
[...]
...The network is trained using the crossentropy error function similar to [7]....
[...]
...and x-vector based signal representations [6], [7] to EEG biometrics....
[...]
...x-vector is a DNN based state-of-the-art speaker recognition technique [7]....
[...]
790 citations
"Subspace techniques for task-indepe..." refers background or methods in this paper
...and x-vector based signal representations [6], [7] to EEG biometrics....
[...]
...i-vector system is one such technique proposed for speaker recognition in [6] and adopted for EEG person identification in [14]....
[...]
...The procedure for training the T -Matrix and thereby extracting ivectors can be found in [6]....
[...]