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/

Zendy Plus

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

Zendy Tools

Zendy Open

Many modern systems for speaker diarization, such as the recently-developedVBx approach, rely on clustering of DNN speaker embeddings followed byresegmentation. Two problems with this approach are that the DNN is notdirectly optimized for this task, and the parameters need significant retuningfor different applications. We have recently presented progress in thisdirection with a Leave-One-Out Gaussian PLDA (LGP) clustering algorithm and anapproach to training the DNN such that embeddings directly optimize performanceof this scoring method. This paper presents a new two-pass version of thissystem, where the second pass uses finer time resolution to significantlyimprove overall performance. For the Callhome corpus, we achieve the firstpublished error rate below 4% without any task-dependent parameter tuning. Wealso show significant progress towards a robust single solution for multiplediarization tasks.

Speaker Diarization using Two-pass Leave-One-Out Gaussian PLDA Clustering of DNN Embeddings