Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890250568> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2890250568 abstract "In the studies of i-vector based speaker verification, the discriminative training of probabilistic linear discriminative analysis (PLDA) model has been proven to be an effective way to improve performance. This paper focuses on using a deep neural network (DNN) to strengthen the original discriminatively trained classifiers by its strong capability of nonlinear modeling representation. We first propose a deep neural network based dimensionality reduction model to replace the linear discriminant analysis (LDA) process, and then a discriminative training algorithm is also proposed to jointly optimize the network and PLDA scoring function under single discriminative criterion. Our experiments show that performance improvements are achieved in the male trials of short2-short3 core data set of NIST SRE08." @default.
- W2890250568 created "2018-09-27" @default.
- W2890250568 creator A5031604617 @default.
- W2890250568 creator A5041058909 @default.
- W2890250568 creator A5065442541 @default.
- W2890250568 date "2018-04-01" @default.
- W2890250568 modified "2023-09-25" @default.
- W2890250568 title "Deep Neural Network Based Discriminative Training for I-Vector/PLDA Speaker Verification" @default.
- W2890250568 cites W2150769028 @default.
- W2890250568 cites W2168561756 @default.
- W2890250568 cites W2183016404 @default.
- W2890250568 cites W2748377523 @default.
- W2890250568 cites W2749358494 @default.
- W2890250568 cites W2963068250 @default.
- W2890250568 doi "https://doi.org/10.1109/icassp.2018.8461344" @default.
- W2890250568 hasPublicationYear "2018" @default.
- W2890250568 type Work @default.
- W2890250568 sameAs 2890250568 @default.
- W2890250568 citedByCount "4" @default.
- W2890250568 countsByYear W28902505682019 @default.
- W2890250568 countsByYear W28902505682020 @default.
- W2890250568 countsByYear W28902505682021 @default.
- W2890250568 crossrefType "proceedings-article" @default.
- W2890250568 hasAuthorship W2890250568A5031604617 @default.
- W2890250568 hasAuthorship W2890250568A5041058909 @default.
- W2890250568 hasAuthorship W2890250568A5065442541 @default.
- W2890250568 hasConcept C111219384 @default.
- W2890250568 hasConcept C119857082 @default.
- W2890250568 hasConcept C153180895 @default.
- W2890250568 hasConcept C154945302 @default.
- W2890250568 hasConcept C17744445 @default.
- W2890250568 hasConcept C199539241 @default.
- W2890250568 hasConcept C2776359362 @default.
- W2890250568 hasConcept C28490314 @default.
- W2890250568 hasConcept C41008148 @default.
- W2890250568 hasConcept C50644808 @default.
- W2890250568 hasConcept C69738355 @default.
- W2890250568 hasConcept C70518039 @default.
- W2890250568 hasConcept C94625758 @default.
- W2890250568 hasConcept C97931131 @default.
- W2890250568 hasConceptScore W2890250568C111219384 @default.
- W2890250568 hasConceptScore W2890250568C119857082 @default.
- W2890250568 hasConceptScore W2890250568C153180895 @default.
- W2890250568 hasConceptScore W2890250568C154945302 @default.
- W2890250568 hasConceptScore W2890250568C17744445 @default.
- W2890250568 hasConceptScore W2890250568C199539241 @default.
- W2890250568 hasConceptScore W2890250568C2776359362 @default.
- W2890250568 hasConceptScore W2890250568C28490314 @default.
- W2890250568 hasConceptScore W2890250568C41008148 @default.
- W2890250568 hasConceptScore W2890250568C50644808 @default.
- W2890250568 hasConceptScore W2890250568C69738355 @default.
- W2890250568 hasConceptScore W2890250568C70518039 @default.
- W2890250568 hasConceptScore W2890250568C94625758 @default.
- W2890250568 hasConceptScore W2890250568C97931131 @default.
- W2890250568 hasLocation W28902505681 @default.
- W2890250568 hasOpenAccess W2890250568 @default.
- W2890250568 hasPrimaryLocation W28902505681 @default.
- W2890250568 hasRelatedWork W1971701369 @default.
- W2890250568 hasRelatedWork W1994207205 @default.
- W2890250568 hasRelatedWork W2013332056 @default.
- W2890250568 hasRelatedWork W2015840095 @default.
- W2890250568 hasRelatedWork W2076431653 @default.
- W2890250568 hasRelatedWork W2105710497 @default.
- W2890250568 hasRelatedWork W2154896604 @default.
- W2890250568 hasRelatedWork W2189305995 @default.
- W2890250568 hasRelatedWork W2242466430 @default.
- W2890250568 hasRelatedWork W2270708757 @default.
- W2890250568 hasRelatedWork W2546246480 @default.
- W2890250568 hasRelatedWork W2548217077 @default.
- W2890250568 hasRelatedWork W2552084856 @default.
- W2890250568 hasRelatedWork W2743873419 @default.
- W2890250568 hasRelatedWork W2890964092 @default.
- W2890250568 hasRelatedWork W2963226429 @default.
- W2890250568 hasRelatedWork W3120912571 @default.
- W2890250568 hasRelatedWork W3202239122 @default.
- W2890250568 hasRelatedWork W51274916 @default.
- W2890250568 hasRelatedWork W2183892672 @default.
- W2890250568 isParatext "false" @default.
- W2890250568 isRetracted "false" @default.
- W2890250568 magId "2890250568" @default.
- W2890250568 workType "article" @default.