Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382536354> ?p ?o ?g. }
- W4382536354 endingPage "887" @default.
- W4382536354 startingPage "883" @default.
- W4382536354 abstract "Robust speaker verification (RSV) under noisy con- ditions is still a challenging task. Recently, some task-specific speech enhancement (SE) approaches are proposed and achieve excellent performance on RSV. However, all these works adopt only one kind of SE network and thus can not remove noise from different aspects, limiting the performance of the RSV task. In this letter, we propose a fused SE framework (FSEF) for RSV, which integrates both T-F masking-based and feature mapping- based SE networks to collect complementary information and improve the robustness against noise. Two FESF-RSV systems are constructed based on two kinds of fusion methods: score fusion and feature fusion. In addition, we present a Multi- Scale Attentive Context Aggregation Network (MSACAN) as the backbone structure in the FSEF. The MSACAN can not only extract and fuse multi-scale features adaptively but also enhance speaker characteristics against noise and interfering speakers. Experiments conducted on the noise-simulated VoxCeleb1 dataset demonstrate both the FSEF and the MSACAN can improve the performance of RSV compared to previous approaches." @default.
- W4382536354 created "2023-06-30" @default.
- W4382536354 creator A5012579399 @default.
- W4382536354 creator A5021697903 @default.
- W4382536354 creator A5042066408 @default.
- W4382536354 creator A5048484794 @default.
- W4382536354 creator A5049638215 @default.
- W4382536354 date "2023-01-01" @default.
- W4382536354 modified "2023-10-15" @default.
- W4382536354 title "A Fused Speech Enhancement Framework for Robust Speaker Verification" @default.
- W4382536354 cites W2194775991 @default.
- W4382536354 cites W2311973309 @default.
- W4382536354 cites W2605589342 @default.
- W4382536354 cites W2696967604 @default.
- W4382536354 cites W2718701456 @default.
- W4382536354 cites W2726515241 @default.
- W4382536354 cites W2746457594 @default.
- W4382536354 cites W2890964092 @default.
- W4382536354 cites W2916104401 @default.
- W4382536354 cites W2922509574 @default.
- W4382536354 cites W2937813194 @default.
- W4382536354 cites W2962866211 @default.
- W4382536354 cites W2963127163 @default.
- W4382536354 cites W2972425344 @default.
- W4382536354 cites W2972443522 @default.
- W4382536354 cites W2982037672 @default.
- W4382536354 cites W3013020904 @default.
- W4382536354 cites W3015598461 @default.
- W4382536354 cites W3024301174 @default.
- W4382536354 cites W3024869864 @default.
- W4382536354 cites W3025783616 @default.
- W4382536354 cites W3088315586 @default.
- W4382536354 cites W3091570562 @default.
- W4382536354 cites W3096964161 @default.
- W4382536354 cites W3103152812 @default.
- W4382536354 cites W3137249133 @default.
- W4382536354 cites W3141035251 @default.
- W4382536354 cites W3174649707 @default.
- W4382536354 cites W3196650842 @default.
- W4382536354 cites W3197013563 @default.
- W4382536354 cites W3198742213 @default.
- W4382536354 cites W4221154746 @default.
- W4382536354 cites W4225682608 @default.
- W4382536354 doi "https://doi.org/10.1109/lsp.2023.3290832" @default.
- W4382536354 hasPublicationYear "2023" @default.
- W4382536354 type Work @default.
- W4382536354 citedByCount "0" @default.
- W4382536354 crossrefType "journal-article" @default.
- W4382536354 hasAuthorship W4382536354A5012579399 @default.
- W4382536354 hasAuthorship W4382536354A5021697903 @default.
- W4382536354 hasAuthorship W4382536354A5042066408 @default.
- W4382536354 hasAuthorship W4382536354A5048484794 @default.
- W4382536354 hasAuthorship W4382536354A5049638215 @default.
- W4382536354 hasConcept C103038307 @default.
- W4382536354 hasConcept C104317684 @default.
- W4382536354 hasConcept C115961682 @default.
- W4382536354 hasConcept C119599485 @default.
- W4382536354 hasConcept C127413603 @default.
- W4382536354 hasConcept C138885662 @default.
- W4382536354 hasConcept C141353440 @default.
- W4382536354 hasConcept C151730666 @default.
- W4382536354 hasConcept C153180895 @default.
- W4382536354 hasConcept C154945302 @default.
- W4382536354 hasConcept C158525013 @default.
- W4382536354 hasConcept C163294075 @default.
- W4382536354 hasConcept C173414695 @default.
- W4382536354 hasConcept C185592680 @default.
- W4382536354 hasConcept C188198153 @default.
- W4382536354 hasConcept C201995342 @default.
- W4382536354 hasConcept C2776182073 @default.
- W4382536354 hasConcept C2779343474 @default.
- W4382536354 hasConcept C2780451532 @default.
- W4382536354 hasConcept C28490314 @default.
- W4382536354 hasConcept C29265498 @default.
- W4382536354 hasConcept C41008148 @default.
- W4382536354 hasConcept C41895202 @default.
- W4382536354 hasConcept C55493867 @default.
- W4382536354 hasConcept C63479239 @default.
- W4382536354 hasConcept C78519656 @default.
- W4382536354 hasConcept C86803240 @default.
- W4382536354 hasConcept C99498987 @default.
- W4382536354 hasConceptScore W4382536354C103038307 @default.
- W4382536354 hasConceptScore W4382536354C104317684 @default.
- W4382536354 hasConceptScore W4382536354C115961682 @default.
- W4382536354 hasConceptScore W4382536354C119599485 @default.
- W4382536354 hasConceptScore W4382536354C127413603 @default.
- W4382536354 hasConceptScore W4382536354C138885662 @default.
- W4382536354 hasConceptScore W4382536354C141353440 @default.
- W4382536354 hasConceptScore W4382536354C151730666 @default.
- W4382536354 hasConceptScore W4382536354C153180895 @default.
- W4382536354 hasConceptScore W4382536354C154945302 @default.
- W4382536354 hasConceptScore W4382536354C158525013 @default.
- W4382536354 hasConceptScore W4382536354C163294075 @default.
- W4382536354 hasConceptScore W4382536354C173414695 @default.
- W4382536354 hasConceptScore W4382536354C185592680 @default.
- W4382536354 hasConceptScore W4382536354C188198153 @default.
- W4382536354 hasConceptScore W4382536354C201995342 @default.
- W4382536354 hasConceptScore W4382536354C2776182073 @default.