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

A good supervised embedding for a specific machine learning task is onlysensitive to changes in the label of interest and is invariant to otherconfounding factors. We leverage the concept of repeatability from measurementtheory to describe this property and propose to use the intra-class correlationcoefficient (ICC) to evaluate the repeatability of embeddings. We then proposea novel regularizer, the ICC regularizer, as a complementary component forcontrastive losses to guide deep neural networks to produce embeddings withhigher repeatability. We use simulated data to explain why the ICC regularizerworks better on minimizing the intra-class variance than the contrastive lossalone. We implement the ICC regularizer and apply it to three speech tasks:speaker verification, voice style conversion, and a clinical application fordetecting dysphonic voice. The experimental results demonstrate that adding anICC regularizer can improve the repeatability of learned embeddings compared toonly using the contrastive loss; further, these embeddings lead to improvedperformance in these downstream tasks.

Learning Repeatable Speech Embeddings Using An Intra-class Correlation Regularizer