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

Verifying the identity of a speaker is crucial in modern human-machineinterfaces, e.g., to ensure privacy protection or to enable biometricauthentication. Classical speaker verification (SV) approaches estimate afixed-dimensional embedding from a speech utterance that encodes the speaker'svoice characteristics. A speaker is verified if his/her voice embedding issufficiently similar to the embedding of the claimed speaker. However, suchapproaches assume that only a single speaker exists in the input. The presenceof concurrent speakers is likely to have detrimental effects on theperformance. To address SV in a multi-speaker environment, we propose anend-to-end deep learning-based SV system that detects whether the targetspeaker exists within an input or not. First, an embedding is estimated from areference utterance to represent the target's characteristics. Second,frame-level features are estimated from the input mixture. The referenceembedding is then fused frame-wise with the mixture's features to allowdistinguishing the target from other speakers on a frame basis. Finally, thefused features are used to predict whether the target speaker is active in thespeech segment or not. Experimental evaluation shows that the proposed methodoutperforms the x-vector in multi-speaker conditions.

Speaker Verification in Multi-Speaker Environments Using Temporal Feature Fusion