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

Recently, we proposed a novel speaker diarization method calledEnd-to-End-Neural-Diarization-vector clustering (EEND-vector clustering) thatintegrates clustering-based and end-to-end neural network-based diarizationapproaches into one framework. The proposed method combines advantages of bothframeworks, i.e. high diarization performance and handling of overlapped speechbased on EEND, and robust handling of long recordings with an arbitrary numberof speakers based on clustering-based approaches. However, the method was onlyevaluated so far on simulated 2-speaker meeting-like data. This paper is to (1)report recent advances we made to this framework, including newly introducedrobust constrained clustering algorithms, and (2) experimentally show that themethod can now significantly outperform competitive diarization methods such asEncoder-Decoder Attractor (EDA)-EEND, on CALLHOME data which comprises realconversational speech data including overlapped speech and an arbitrary numberof speakers. By further analyzing the experimental results, this paper alsodiscusses pros and cons of the proposed method and reveals potential forfurther improvement. A set of the code to reproduce the results is available athttps://github.com/nttcslab-sp/EEND-vector-clustering.

Advances in integration of end-to-end neural and clustering-based diarization for real conversational speech