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

Speaker verification is an established yet challenging task in speechprocessing and a very vibrant research area. Recent speaker verification (SV)systems rely on deep neural networks to extract high-level embeddings which areable to characterize the users' voices. Most of the studies have investigatedon improving the discriminability of the networks to extract better embeddingsfor performances improvement. However, only few research focus on improving thegeneralization. In this paper, we propose to apply the ladder network frameworkin the SV systems, which combines the supervised and unsupervised learningfashions. The ladder network can make the system to have better high-levelembedding by balancing the trade-off to keep/discard as much useful/uselessinformation as possible. We evaluated the framework on two state-of-the-art SVsystems, d-vector and x-vector, which can be used for different use cases. Theexperiments showed that the proposed approach relatively improved theperformance by 10% at most without adding parameters and augmented data.

Improving Embedding Extraction for Speaker Verification with Ladder Network