Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048754967> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3048754967 abstract "Deep neural networks (DNN) have recently been widely used in speaker recognition systems, achieving state-of-the-art performance on various benchmarks. The x-vector architecture is especially popular in this research community, due to its excellent performance and manageable computational complexity. In this paper, we present the lrx-vector system, which is the low-rank factorized version of the x-vector embedding network. The primary objective of this topology is to further reduce the memory requirement of the speaker recognition system. We discuss the deployment of knowledge distillation for training the lrx-vector system and compare against low-rank factorization with SVD. On the VOiCES 2019 far-field corpus we were able to reduce the weights by 28% compared to the full-rank x-vector system while keeping the recognition rate constant (1.83% EER)." @default.
- W3048754967 created "2020-08-18" @default.
- W3048754967 creator A5033302750 @default.
- W3048754967 creator A5040558849 @default.
- W3048754967 creator A5079026336 @default.
- W3048754967 date "2020-08-11" @default.
- W3048754967 modified "2023-09-27" @default.
- W3048754967 title "Compact Speaker Embedding: lrx-vector" @default.
- W3048754967 cites W1499864241 @default.
- W3048754967 cites W1524333225 @default.
- W3048754967 cites W1589137271 @default.
- W3048754967 cites W1798945469 @default.
- W3048754967 cites W1821462560 @default.
- W3048754967 cites W2053134102 @default.
- W3048754967 cites W2114925438 @default.
- W3048754967 cites W2136682440 @default.
- W3048754967 cites W2172166488 @default.
- W3048754967 cites W2233116163 @default.
- W3048754967 cites W2295405790 @default.
- W3048754967 cites W2408183654 @default.
- W3048754967 cites W2516631658 @default.
- W3048754967 cites W2535503132 @default.
- W3048754967 cites W2593116425 @default.
- W3048754967 cites W2612434969 @default.
- W3048754967 cites W2758584002 @default.
- W3048754967 cites W2763188033 @default.
- W3048754967 cites W2776638780 @default.
- W3048754967 cites W2890964092 @default.
- W3048754967 cites W2896538040 @default.
- W3048754967 cites W2902347140 @default.
- W3048754967 cites W2916024349 @default.
- W3048754967 cites W2938358845 @default.
- W3048754967 cites W2950517223 @default.
- W3048754967 cites W2963040451 @default.
- W3048754967 cites W2963456629 @default.
- W3048754967 cites W2972697221 @default.
- W3048754967 cites W2973062377 @default.
- W3048754967 cites W2981087920 @default.
- W3048754967 cites W2981505889 @default.
- W3048754967 cites W3103152812 @default.
- W3048754967 hasPublicationYear "2020" @default.
- W3048754967 type Work @default.
- W3048754967 sameAs 3048754967 @default.
- W3048754967 citedByCount "0" @default.
- W3048754967 crossrefType "posted-content" @default.
- W3048754967 hasAuthorship W3048754967A5033302750 @default.
- W3048754967 hasAuthorship W3048754967A5040558849 @default.
- W3048754967 hasAuthorship W3048754967A5079026336 @default.
- W3048754967 hasConcept C114614502 @default.
- W3048754967 hasConcept C133892786 @default.
- W3048754967 hasConcept C153180895 @default.
- W3048754967 hasConcept C154945302 @default.
- W3048754967 hasConcept C164226766 @default.
- W3048754967 hasConcept C28490314 @default.
- W3048754967 hasConcept C33923547 @default.
- W3048754967 hasConcept C41008148 @default.
- W3048754967 hasConcept C41608201 @default.
- W3048754967 hasConcept C50644808 @default.
- W3048754967 hasConceptScore W3048754967C114614502 @default.
- W3048754967 hasConceptScore W3048754967C133892786 @default.
- W3048754967 hasConceptScore W3048754967C153180895 @default.
- W3048754967 hasConceptScore W3048754967C154945302 @default.
- W3048754967 hasConceptScore W3048754967C164226766 @default.
- W3048754967 hasConceptScore W3048754967C28490314 @default.
- W3048754967 hasConceptScore W3048754967C33923547 @default.
- W3048754967 hasConceptScore W3048754967C41008148 @default.
- W3048754967 hasConceptScore W3048754967C41608201 @default.
- W3048754967 hasConceptScore W3048754967C50644808 @default.
- W3048754967 hasLocation W30487549671 @default.
- W3048754967 hasOpenAccess W3048754967 @default.
- W3048754967 hasPrimaryLocation W30487549671 @default.
- W3048754967 hasRelatedWork W1486634905 @default.
- W3048754967 hasRelatedWork W1836816248 @default.
- W3048754967 hasRelatedWork W194799689 @default.
- W3048754967 hasRelatedWork W1992048767 @default.
- W3048754967 hasRelatedWork W1993482042 @default.
- W3048754967 hasRelatedWork W2055753704 @default.
- W3048754967 hasRelatedWork W2063610652 @default.
- W3048754967 hasRelatedWork W2075417325 @default.
- W3048754967 hasRelatedWork W2135531184 @default.
- W3048754967 hasRelatedWork W2140128461 @default.
- W3048754967 hasRelatedWork W2161231759 @default.
- W3048754967 hasRelatedWork W2184780472 @default.
- W3048754967 hasRelatedWork W2200560475 @default.
- W3048754967 hasRelatedWork W2293711698 @default.
- W3048754967 hasRelatedWork W2964130064 @default.
- W3048754967 hasRelatedWork W3097731653 @default.
- W3048754967 hasRelatedWork W3162595998 @default.
- W3048754967 hasRelatedWork W8388691 @default.
- W3048754967 hasRelatedWork W97788045 @default.
- W3048754967 hasRelatedWork W3088079025 @default.
- W3048754967 isParatext "false" @default.
- W3048754967 isRetracted "false" @default.
- W3048754967 magId "3048754967" @default.
- W3048754967 workType "article" @default.