Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
×
This paper introduces and evaluates a novel approach for unsupervised speaker change detection. In many unsupervised speaker change detection algorithms, ...
This is accomplished by estimating the speech segment by two mixtures of Gaussian mixture model and estimating the left and right segments around the ...
Oct 22, 2024 · In this paper, we are interested in detecting changes in speaker identity, environmental condition and channel condition; we call this the ...
Missing: Kernel- | Show results with:Kernel-
This two step process of alternately calculating the expectation (10) and updating the the sufficient statistics (11) is iterated until some convergence ...
A new approach to speaker change detection is proposed and investigated. The method, which is based on a probabilistic framework, provides an effective means ...
Most conventional speaker recognition systems use Gaussian mixture models ... Robust Text-Independent Speaker Identification Using. Gaussian Mixture Speaker ...
In this paper, we propose a new approach to robust speaker identification using KPCA (kernel principal component analysis). This approach uses ensembles of ...
Missing: detection | Show results with:detection
We propose a tree-based kernel selection (TBKS) algorithm as a computationally efficient approach to the Gaussian mixture model–universal background model (GMM ...
Campbell13 proposed Gaussian mixture model (GMM) super-vector based on the in-depth study of GMM parameters and maximum a posteriori (MAP) algorithm. He ...
Jul 6, 2023 · The basic framework of the Stacked Auto-encoders based speaker recognition model can be illustrated in Fig. 1. After pre-processing and feature ...