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 great challenge in speaker representation learning using deep models is todesign learning objectives that can enhance the discrimination of unseenspeakers under unseen domains. This work proposes a supervised contrastivelearning objective to learn a speaker embedding space by effectively leveragingthe label information in the training data. In such a space, utterance pairsspoken by the same or similar speakers will stay close, while utterance pairsspoken by different speakers will be far apart. For each training speaker, weperform random data augmentation on their utterances to form positive pairs,and utterances from different speakers form negative pairs. To maximize speakerseparability in the embedding space, we incorporate the additive angular-marginloss into the contrastive learning objective. Experimental results on CN-Celebshow that this new learning objective can cause ECAPA-TDNN to find an embeddingspace that exhibits great speaker discrimination. The contrastive learningobjective is easy to implement, and we provide PyTorch code athttps://github.com/shanmon110/AAMSupCon.

Speaker Representation Learning via Contrastive Loss with Maximal Speaker Separability