The universal background model (UBM) is an effective framework widely used in speaker recognition. But so far it has received little attention from the speech recognition field. In this work, we make a first attempt to apply the UBM to acoustic modeling in ASR. We propose a tree-based parameter

In this paper, we have investigated into JFA used for speaker recognition. First, we performed systematic comparison of full JFA with its simplified variants and confirmed superior per-formance of the full JFA with both eigenchannels and eigen-voices. We investigated into sensitivity of JFA on the number of eigenvoices both for the full one and simplified variants. We studied the importance of normalization and found that gender-dependent zt-norm was crucial. The results are reported on

as a score normalization technique is studied for the case of dynamic signature verification. This technique is commonly used in speaker verification systems. Background Models are tested in two different systems based on global features: one based on Parzen Windows and another based on adapted

but effective GMMs for likelihood functions, a universal background model (UBM) for alternative speaker representation, and a form of Bayesian adaptation to derive speaker models from the UBM. The development and use of a handset detector and score normalization to greatly improve verification performance

- Universal Background Model (GMM-UBM). The feature vectors are categorized into three sets, which include reliable speech, doubtful speech and unreliable speech. Then a novel distance measure is presented for real-time speaker change detection. Extensive experiments demonstrate the superior performance

Abstract. We aim to describe different approaches for vector quantization in Automatic Speaker Verification. We designed our novel architecture based on multiples codebook representing the speakers and the impostor model called universal background model and compared it to another vector

Abstract. Background subtraction is a method typically used to seg-ment moving regions in image sequences taken from a static camera by comparing each new frame to a model of the scene background. We present a novel non-parametric background model and a background subtraction approach. The model

The University of Florida Sparse Matrix Collection is a large, widely available, and actively growing set of sparse matrices that arise in real applications. Its matrices cover a wide spectrum of problem domains, both those arising from problems with underlying 2D or 3D geometry (structural

In this paper we propose to use Variational Bayesian Analysis (VBA) instead of Maximum Likelihood (ML) estimation for Universal Background Model (UBM) building in GMM text independent speaker verification systems. Using VBA estimation solves the problem of the optimal choice of the UBM mixture

A universal algorithm for sequential data compression is presented. Its performance is investigated with respect to a nonprobabilistic model of constrained sources. The compression ratio achieved by the proposed universal code uniformly approaches the lower bounds on the compression ratios