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

Speech utterances recorded under differing conditions exhibit varying degreesof confidence in their embedding estimates, i.e., uncertainty, even if they areextracted using the same neural network. This paper aims to incorporate theuncertainty estimate produced in the xi-vector network front-end with aprobabilistic linear discriminant analysis (PLDA) back-end scoring for speakerverification. To achieve this we derive a posterior covariance matrix, whichmeasures the uncertainty, from the frame-wise precisions to the embeddingspace. We propose a log-likelihood ratio function for the PLDA scoring with theuncertainty propagation. We also propose to replace the length normalizationpre-processing technique with a length scaling technique for the application ofuncertainty propagation in the back-end. Experimental results on theVoxCeleb-1, SITW test sets as well as a domain-mismatched CNCeleb1-E set showthe effectiveness of the proposed techniques with 14.5%-41.3% EER reductionsand 4.6%-25.3% minDCF reductions.

Incorporating Uncertainty from Speaker Embedding Estimation to Speaker Verification