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

Background noise considerably reduces the accuracy and reliability of speakerverification (SV) systems. These challenges can be addressed using a speechenhancement system as a front-end module. Recently, diffusion probabilisticmodels (DPMs) have exhibited remarkable noise-compensation capabilities in thespeech enhancement domain. Building on this success, we propose Diff-SV, anoise-robust SV framework that leverages DPM. Diff-SV unifies a DPM-basedspeech enhancement system with a speaker embedding extractor, and yields adiscriminative and noise-tolerable speaker representation through ahierarchical structure. The proposed model was evaluated under both in-domainand out-of-domain noisy conditions using the VoxCeleb1 test set, an externalnoise source, and the VOiCES corpus. The obtained experimental resultsdemonstrate that Diff-SV achieves state-of-the-art performance, outperformingrecently proposed noise-robust SV systems.

Diff-SV: A Unified Hierarchical Framework for Noise-Robust Speaker Verification Using Score-Based Diffusion Probabilistic Models