Matches in SemOpenAlex for { <https://semopenalex.org/work/W2937952020> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W2937952020 abstract "Neural network based attention modeling has found utility in areas such as visual analysis, speech recognition and more recently speaker recognition. Attention represents a gating (or weighting) function on information and governs how the corresponding statistics are accumulated. In the context of speaker recognition, attention can be incorporated as a frame weighted mean of an information stream. These weights can be made to sum to one (the standard approach) or be calculated in other ways. If the weights can be made to represent event observation probabilities, we can extend the approach to be within a Bayesian framework. More specifically, we combine prior information with the frame weighted statistics to produce an adapted or posterior estimate of the mean. We evaluate the proposed method on NIST data." @default.
- W2937952020 created "2019-04-25" @default.
- W2937952020 creator A5029030495 @default.
- W2937952020 creator A5064879195 @default.
- W2937952020 date "2019-05-01" @default.
- W2937952020 modified "2023-10-18" @default.
- W2937952020 title "A Bayesian Attention Neural Network Layer for Speaker Recognition" @default.
- W2937952020 cites W1494198834 @default.
- W2937952020 cites W2041823554 @default.
- W2937952020 cites W2078169166 @default.
- W2937952020 cites W2100969003 @default.
- W2937952020 cites W2114925438 @default.
- W2937952020 cites W2121812409 @default.
- W2937952020 cites W2138547132 @default.
- W2937952020 cites W2726515241 @default.
- W2937952020 cites W2748488820 @default.
- W2937952020 cites W2889519245 @default.
- W2937952020 cites W2890964092 @default.
- W2937952020 cites W4234330420 @default.
- W2937952020 doi "https://doi.org/10.1109/icassp.2019.8682953" @default.
- W2937952020 hasPublicationYear "2019" @default.
- W2937952020 type Work @default.
- W2937952020 sameAs 2937952020 @default.
- W2937952020 citedByCount "4" @default.
- W2937952020 countsByYear W29379520202020 @default.
- W2937952020 countsByYear W29379520202021 @default.
- W2937952020 countsByYear W29379520202022 @default.
- W2937952020 countsByYear W29379520202023 @default.
- W2937952020 crossrefType "proceedings-article" @default.
- W2937952020 hasAuthorship W2937952020A5029030495 @default.
- W2937952020 hasAuthorship W2937952020A5064879195 @default.
- W2937952020 hasConcept C107673813 @default.
- W2937952020 hasConcept C133892786 @default.
- W2937952020 hasConcept C153180895 @default.
- W2937952020 hasConcept C154945302 @default.
- W2937952020 hasConcept C178790620 @default.
- W2937952020 hasConcept C185592680 @default.
- W2937952020 hasConcept C2779227376 @default.
- W2937952020 hasConcept C28490314 @default.
- W2937952020 hasConcept C2984842247 @default.
- W2937952020 hasConcept C33724603 @default.
- W2937952020 hasConcept C41008148 @default.
- W2937952020 hasConcept C50644808 @default.
- W2937952020 hasConceptScore W2937952020C107673813 @default.
- W2937952020 hasConceptScore W2937952020C133892786 @default.
- W2937952020 hasConceptScore W2937952020C153180895 @default.
- W2937952020 hasConceptScore W2937952020C154945302 @default.
- W2937952020 hasConceptScore W2937952020C178790620 @default.
- W2937952020 hasConceptScore W2937952020C185592680 @default.
- W2937952020 hasConceptScore W2937952020C2779227376 @default.
- W2937952020 hasConceptScore W2937952020C28490314 @default.
- W2937952020 hasConceptScore W2937952020C2984842247 @default.
- W2937952020 hasConceptScore W2937952020C33724603 @default.
- W2937952020 hasConceptScore W2937952020C41008148 @default.
- W2937952020 hasConceptScore W2937952020C50644808 @default.
- W2937952020 hasLocation W29379520201 @default.
- W2937952020 hasOpenAccess W2937952020 @default.
- W2937952020 hasPrimaryLocation W29379520201 @default.
- W2937952020 hasRelatedWork W1563120900 @default.
- W2937952020 hasRelatedWork W2312116756 @default.
- W2937952020 hasRelatedWork W2380536744 @default.
- W2937952020 hasRelatedWork W2384122842 @default.
- W2937952020 hasRelatedWork W2736005052 @default.
- W2937952020 hasRelatedWork W2773120646 @default.
- W2937952020 hasRelatedWork W2778699561 @default.
- W2937952020 hasRelatedWork W2794558692 @default.
- W2937952020 hasRelatedWork W2893763841 @default.
- W2937952020 hasRelatedWork W2992140536 @default.
- W2937952020 isParatext "false" @default.
- W2937952020 isRetracted "false" @default.
- W2937952020 magId "2937952020" @default.
- W2937952020 workType "article" @default.