FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4372267288> ?p ?o ?g. }

• W4372267288 abstract "Automatic speaker verification (ASV) suffers from performance degradation in noisy environments. To solve this problem, we propose the noise-disentanglement metric learning to reduce the speaker-irrelevant noisy components and build a noise-invariant embedding space. Specifically, the disentanglement module, including the speaker encoder and re-construction module, is dedicated to decoupling speech signals. The speaker encoder is used to disentangle speaker-related components, and the reconstruction module increases the model’s ability to constrain the noise information by re-constructing the signal. In addition, distribution optimization is introduced to supervise the spatial structure of speaker embeddings under noisy environments. Experiments on Vox-Celeb1 indicate that the proposed method improves the performance of the speaker verification system in both clean and noisy conditions." @default.
• W4372267288 created "2023-05-07" @default.
• W4372267288 creator A5002847748 @default.
• W4372267288 creator A5004287909 @default.
• W4372267288 creator A5017251198 @default.
• W4372267288 creator A5041985945 @default.
• W4372267288 creator A5050763764 @default.
• W4372267288 creator A5087592842 @default.
• W4372267288 date "2023-06-04" @default.
• W4372267288 modified "2023-10-14" @default.
• W4372267288 title "Noise-Disentanglement Metric Learning for Robust Speaker Verification" @default.
• W4372267288 cites W1936725236 @default.
• W4372267288 cites W2055611715 @default.
• W4372267288 cites W2090716422 @default.
• W4372267288 cites W2117671523 @default.
• W4372267288 cites W2150769028 @default.
• W4372267288 cites W2159202424 @default.
• W4372267288 cites W2407127962 @default.
• W4372267288 cites W2513927927 @default.
• W4372267288 cites W2604341542 @default.
• W4372267288 cites W2746742816 @default.
• W4372267288 cites W2890964092 @default.
• W4372267288 cites W2982037672 @default.
• W4372267288 cites W3015231328 @default.
• W4372267288 cites W3196650842 @default.
• W4372267288 cites W4206633762 @default.
• W4372267288 cites W4224927738 @default.
• W4372267288 cites W4321780088 @default.
• W4372267288 doi "https://doi.org/10.1109/icassp49357.2023.10096848" @default.
• W4372267288 hasPublicationYear "2023" @default.
• W4372267288 type Work @default.
• W4372267288 citedByCount "0" @default.
• W4372267288 crossrefType "proceedings-article" @default.
• W4372267288 hasAuthorship W4372267288A5002847748 @default.
• W4372267288 hasAuthorship W4372267288A5004287909 @default.
• W4372267288 hasAuthorship W4372267288A5017251198 @default.
• W4372267288 hasAuthorship W4372267288A5041985945 @default.
• W4372267288 hasAuthorship W4372267288A5050763764 @default.
• W4372267288 hasAuthorship W4372267288A5087592842 @default.
• W4372267288 hasBestOaLocation W43722672881 @default.
• W4372267288 hasConcept C104317684 @default.
• W4372267288 hasConcept C111919701 @default.
• W4372267288 hasConcept C115961682 @default.
• W4372267288 hasConcept C118505674 @default.
• W4372267288 hasConcept C127413603 @default.
• W4372267288 hasConcept C133731056 @default.
• W4372267288 hasConcept C133892786 @default.
• W4372267288 hasConcept C153180895 @default.
• W4372267288 hasConcept C154945302 @default.
• W4372267288 hasConcept C163294075 @default.
• W4372267288 hasConcept C176217482 @default.
• W4372267288 hasConcept C185592680 @default.
• W4372267288 hasConcept C190470478 @default.
• W4372267288 hasConcept C205606062 @default.
• W4372267288 hasConcept C21547014 @default.
• W4372267288 hasConcept C28490314 @default.
• W4372267288 hasConcept C29265498 @default.
• W4372267288 hasConcept C2982762665 @default.
• W4372267288 hasConcept C33923547 @default.
• W4372267288 hasConcept C37914503 @default.
• W4372267288 hasConcept C41008148 @default.
• W4372267288 hasConcept C41608201 @default.
• W4372267288 hasConcept C55493867 @default.
• W4372267288 hasConcept C63479239 @default.
• W4372267288 hasConcept C99498987 @default.
• W4372267288 hasConceptScore W4372267288C104317684 @default.
• W4372267288 hasConceptScore W4372267288C111919701 @default.
• W4372267288 hasConceptScore W4372267288C115961682 @default.
• W4372267288 hasConceptScore W4372267288C118505674 @default.
• W4372267288 hasConceptScore W4372267288C127413603 @default.
• W4372267288 hasConceptScore W4372267288C133731056 @default.
• W4372267288 hasConceptScore W4372267288C133892786 @default.
• W4372267288 hasConceptScore W4372267288C153180895 @default.
• W4372267288 hasConceptScore W4372267288C154945302 @default.
• W4372267288 hasConceptScore W4372267288C163294075 @default.
• W4372267288 hasConceptScore W4372267288C176217482 @default.
• W4372267288 hasConceptScore W4372267288C185592680 @default.
• W4372267288 hasConceptScore W4372267288C190470478 @default.
• W4372267288 hasConceptScore W4372267288C205606062 @default.
• W4372267288 hasConceptScore W4372267288C21547014 @default.
• W4372267288 hasConceptScore W4372267288C28490314 @default.
• W4372267288 hasConceptScore W4372267288C29265498 @default.
• W4372267288 hasConceptScore W4372267288C2982762665 @default.
• W4372267288 hasConceptScore W4372267288C33923547 @default.
• W4372267288 hasConceptScore W4372267288C37914503 @default.
• W4372267288 hasConceptScore W4372267288C41008148 @default.
• W4372267288 hasConceptScore W4372267288C41608201 @default.
• W4372267288 hasConceptScore W4372267288C55493867 @default.
• W4372267288 hasConceptScore W4372267288C63479239 @default.
• W4372267288 hasConceptScore W4372267288C99498987 @default.
• W4372267288 hasFunder F4320321001 @default.
• W4372267288 hasLocation W43722672881 @default.
• W4372267288 hasOpenAccess W4372267288 @default.
• W4372267288 hasPrimaryLocation W43722672881 @default.
• W4372267288 hasRelatedWork W2336323613 @default.
• W4372267288 hasRelatedWork W2588576637 @default.
• W4372267288 hasRelatedWork W3015923889 @default.
• W4372267288 hasRelatedWork W3094723376 @default.
• W4372267288 hasRelatedWork W3114320604 @default.
• W4372267288 hasRelatedWork W3179294409 @default.

• next