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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper presents a new deep clustering (DC) method called manifold-awareDC (M-DC) that can enhance hyperspace utilization more effectively than theoriginal DC. The original DC has a limitation in that a pair of two speakershas to be embedded having an orthogonal relationship due to its use of theone-hot vector-based loss function, while our method derives a unique lossfunction aimed at maximizing the target angle in the hyperspace based on thenature of a regular simplex. Our proposed loss imposes a higher penalty thanthe original DC when the speaker is assigned incorrectly. The change from DC toM-DC can be easily achieved by rewriting just one term in the loss function ofDC, without any other modifications to the network architecture or modelparameters. As such, our method has high practicability because it does notaffect the original inference part. The experimental results show that theproposed method improves the performances of the original DC and its expansionmethod.

Manifold-Aware Deep Clustering: Maximizing Angles between Embedding Vectors Based on Regular Simplex