Traditional speech enhancement (SE) methods have been employed to improve the performance of speaker verification systems.
Adapted Gaussian mixture models (GMMs) were implemented to investigate the performance of speaker verification technology for distinguishing identical twins in 2005 [10].
Pixel-based features are suited for fast candidate search, whereas more significant region-based features improve the performance of candidate verification.
The value where FPR = FNR is called equal error rate (EER) and is widely used to determine performance of a verification system as a single parameter.
First, the performance of face verification systems in PCA and LDA feature spaces with different similarity measure classifiers was experimentally evaluated.
Over the past few years, many approaches based on the use of Gaussian mixture models (GMM) in a GMM universal background model (GMM-UBM) framework [7] have been proposed to improve the performance of speaker verification system.
We implemented our method on OpenStack using Jenkins and evaluated the feasibility of its functions, the effectiveness of reducing test case preparation costs, and the performance of automatic verification.
Similarly, the performance of writer verification systems is represented through receiver operating characteristic (ROC) curves and is quantified through area under the curve (AUC) or equal error rates (EER).
The performance of face verification systems using different similarity measures in two well-known appearance-based representation spaces, namely Principle Component Analysis (PCA) and Linear Discriminant Analysis (LDA) is experimentally studied.
Although, the PCA-based classifiers perform nearly 3 times worse than the LDA-based one, an interesting finding of this paper compared to our previous work [19] is that the performance of the verification system can be further improved by fusing the LDA- and PCA-based classifiers.
The performance of the verification models was quite similar to that of the training data.
