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

The objective of this work is to train noise-robust speaker embeddingsadapted for speaker diarisation. Speaker embeddings play a crucial role in theperformance of diarisation systems, but they often capture spurious informationsuch as noise, adversely affecting performance. Our previous work has proposedan auto-encoder-based dimensionality reduction module to help remove theredundant information. However, they do not explicitly separate suchinformation and have also been found to be sensitive to hyper-parameter values.To this end, we propose two contributions to overcome these issues: (i) a noveldimensionality reduction framework that can disentangle spurious informationfrom the speaker embeddings; (ii) the use of speech activity vector to preventthe speaker code from representing the background noise. Through a range ofexperiments conducted on four datasets, our approach consistently demonstratesthe state-of-the-art performance among models without system fusion.

Advancing the dimensionality reduction of speaker embeddings for speaker diarisation: disentangling noise and informing speech activity