Shared latent subspace modelling within Gaussian-Binary Restricted Boltzmann Machines for NIST i-Vector Challenge 2014
This paper presents a novel approach to speaker subspace modelling based on Gaussian-Binary Restricted Boltzmann Machines (GRBM). The proposed model is based on the idea of shared factors as in the Probabilistic Linear Discriminant Analysis (PLDA). GRBM hidden layer is divided into speaker and channel factors, herein the speaker factor is shared over all vectors of the speaker. Then Maximum Likelihood Parameter Estimation (MLE) for proposed model is introduced. Various new scoring techniques for speaker verification using GRBM are proposed. The results for NIST i-vector Challenge 2014 dataset are presented.
Code (0)
등록된 구현이 없습니다.
Tasks
parameter estimationSpeaker VerificationSimilar Papers 제목 키워드 기반
Lightweight yet Fine-grained: A Graph Capsule Convolutional Network with Subspace Alignment for Shared-account Sequential Recommendation
Shared-account Sequential Recommendation (SSR) aims to provide personalized recommendations for accounts shared by multiple users with varying sequential preferences. Previous studies on SSR struggle to capture the fine-…
Sequential RecommendationBayesian Alignments of Warped Multi-Output Gaussian Processes
We propose a novel Bayesian approach to modelling nonlinear alignments of time series based on latent shared information. We apply the method to the real-world problem of finding common structure in the sensor data of wi…
Gaussian ProcessesTime SeriesTime Series AnalysisTime-Resolved fMRI Shared Response Model using Gaussian Process Factor Analysis
Multi-subject fMRI studies are challenging due to the high variability of both brain anatomy and functional brain topographies across participants. An effective way of aggregating multi-subject fMRI data is to extract a …
AnatomyIdentifying signal and noise structure in neural population activity with Gaussian process factor models
Neural datasets often contain measurements of neural activity across multiple trials of a repeated stimulus or behavior. An important problem in the analysis of such datasets is to characterize systematic aspects of neur…
Variational InferenceSpectral learning of linear dynamics from generalised-linear observations with application to neural population data
Latent linear dynamical systems with generalised-linear observation models arise in a variety of applications, for example when modelling the spiking activity of populations of neurons. Here, we show how spectral learn…