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

This report describes the NPU-HC speaker verification system submitted to theO-COCOSDA Multi-lingual Speaker Verification (MSV) Challenge 2022, whichfocuses on developing speaker verification systems for low-resource Asianlanguages. We participate in the I-MSV track, which aims to develop speakerverification systems for various Indian languages. In this challenge, we firstexplore different neural network frameworks for low-resource speakerverification. Then we leverage vanilla fine-tuning and weight transferfine-tuning to transfer the out-domain pre-trained models to the in-domainIndian dataset. Specifically, the weight transfer fine-tuning aims to constrainthe distance of the weights between the pre-trained model and the fine-tunedmodel, which takes advantage of the previously acquired discriminative abilityfrom the large-scale out-domain datasets and avoids catastrophic forgetting andoverfitting at the same time. Finally, score fusion is adopted to furtherimprove performance. Together with the above contributions, we obtain 0.223%EER on the public evaluation set, ranking 2nd place on the leaderboard. On theprivate evaluation set, the EER of our submitted system is 2.123% and 0.630%for the constrained and unconstrained sub-tasks of the I-MSV track, leading tothe 1st and 3rd place in the ranking, respectively.

MSV Challenge 2022: NPU-HC Speaker Verification System for Low-resource Indian Languages