English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

State-of-the-art i-vector based speaker verification relies on variants ofProbabilistic Linear Discriminant Analysis (PLDA) for discriminant analysis. Weare mainly motivated by the recent work of the joint Bayesian (JB) method,which is originally proposed for discriminant analysis in face verification. Weapply JB to speaker verification and make three contributions beyond theoriginal JB. 1) In contrast to the EM iterations with approximated statisticsin the original JB, the EM iterations with exact statistics are employed andgive better performance. 2) We propose to do simultaneous diagonalization (SD)of the within-class and between-class covariance matrices to achieve efficienttesting, which has broader application scope than the SVD-based efficienttesting method in the original JB. 3) We scrutinize similarities anddifferences between various Gaussian PLDAs and JB, complementing the previousanalysis of comparing JB only with Prince-Elder PLDA. Extensive experiments areconducted on NIST SRE10 core condition 5, empirically validating thesuperiority of JB with faster convergence rate and 9-13% EER reduction comparedwith state-of-the-art PLDA.

Joint Bayesian Gaussian discriminant analysis for speaker verification