Matches in SemOpenAlex for { <https://semopenalex.org/work/W2938291464> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2938291464 abstract "In this work, we continue in our research on i-vector extractor for speaker verification (SV) and we optimize its architecture for fast and effective discriminative training. We were motivated by computational and memory requirements caused by the large number of parameters of the original generative i-vector model. Our aim is to preserve the power of the original generative model, and at the same time focus the model towards extraction of speaker-related information. We show that it is possible to represent a standard generative i-vector extractor by a model with significantly less parameters and obtain similar performance on SV tasks. We can further refine this compact model by discriminative training and obtain i-vectors that lead to better performance on various SV benchmarks representing different acoustic domains." @default.
- W2938291464 created "2019-04-25" @default.
- W2938291464 creator A5008717681 @default.
- W2938291464 creator A5042273299 @default.
- W2938291464 creator A5064238041 @default.
- W2938291464 creator A5075269577 @default.
- W2938291464 date "2019-04-05" @default.
- W2938291464 modified "2023-09-26" @default.
- W2938291464 title "Factorization of Discriminatively Trained i-vector Extractor for Speaker Recognition" @default.
- W2938291464 cites W2039057510 @default.
- W2938291464 cites W2046056978 @default.
- W2938291464 cites W2075581860 @default.
- W2938291464 cites W2114925438 @default.
- W2938291464 cites W2150769028 @default.
- W2938291464 cites W2167136086 @default.
- W2938291464 cites W2395619480 @default.
- W2938291464 cites W2402626018 @default.
- W2938291464 cites W2491474862 @default.
- W2938291464 cites W2516764878 @default.
- W2938291464 cites W2584329820 @default.
- W2938291464 cites W2586956420 @default.
- W2938291464 cites W2587150483 @default.
- W2938291464 cites W2746742816 @default.
- W2938291464 cites W2748488820 @default.
- W2938291464 cites W2805332618 @default.
- W2938291464 cites W2890964092 @default.
- W2938291464 cites W2963095666 @default.
- W2938291464 cites W35904254 @default.
- W2938291464 cites W58456301 @default.
- W2938291464 hasPublicationYear "2019" @default.
- W2938291464 type Work @default.
- W2938291464 sameAs 2938291464 @default.
- W2938291464 citedByCount "0" @default.
- W2938291464 crossrefType "posted-content" @default.
- W2938291464 hasAuthorship W2938291464A5008717681 @default.
- W2938291464 hasAuthorship W2938291464A5042273299 @default.
- W2938291464 hasAuthorship W2938291464A5064238041 @default.
- W2938291464 hasAuthorship W2938291464A5075269577 @default.
- W2938291464 hasConcept C117978034 @default.
- W2938291464 hasConcept C120665830 @default.
- W2938291464 hasConcept C121332964 @default.
- W2938291464 hasConcept C127413603 @default.
- W2938291464 hasConcept C153180895 @default.
- W2938291464 hasConcept C154945302 @default.
- W2938291464 hasConcept C167966045 @default.
- W2938291464 hasConcept C192209626 @default.
- W2938291464 hasConcept C21880701 @default.
- W2938291464 hasConcept C28490314 @default.
- W2938291464 hasConcept C39890363 @default.
- W2938291464 hasConcept C41008148 @default.
- W2938291464 hasConcept C97931131 @default.
- W2938291464 hasConceptScore W2938291464C117978034 @default.
- W2938291464 hasConceptScore W2938291464C120665830 @default.
- W2938291464 hasConceptScore W2938291464C121332964 @default.
- W2938291464 hasConceptScore W2938291464C127413603 @default.
- W2938291464 hasConceptScore W2938291464C153180895 @default.
- W2938291464 hasConceptScore W2938291464C154945302 @default.
- W2938291464 hasConceptScore W2938291464C167966045 @default.
- W2938291464 hasConceptScore W2938291464C192209626 @default.
- W2938291464 hasConceptScore W2938291464C21880701 @default.
- W2938291464 hasConceptScore W2938291464C28490314 @default.
- W2938291464 hasConceptScore W2938291464C39890363 @default.
- W2938291464 hasConceptScore W2938291464C41008148 @default.
- W2938291464 hasConceptScore W2938291464C97931131 @default.
- W2938291464 hasLocation W29382914641 @default.
- W2938291464 hasOpenAccess W2938291464 @default.
- W2938291464 hasPrimaryLocation W29382914641 @default.
- W2938291464 hasRelatedWork W1547774380 @default.
- W2938291464 hasRelatedWork W2034961825 @default.
- W2938291464 hasRelatedWork W2093028810 @default.
- W2938291464 hasRelatedWork W2404380129 @default.
- W2938291464 hasRelatedWork W2467417825 @default.
- W2938291464 hasRelatedWork W2554224824 @default.
- W2938291464 hasRelatedWork W2561210505 @default.
- W2938291464 hasRelatedWork W2606778926 @default.
- W2938291464 hasRelatedWork W2612122134 @default.
- W2938291464 hasRelatedWork W2626212216 @default.
- W2938291464 hasRelatedWork W2794556139 @default.
- W2938291464 hasRelatedWork W2898645116 @default.
- W2938291464 hasRelatedWork W2921764497 @default.
- W2938291464 hasRelatedWork W2923488656 @default.
- W2938291464 hasRelatedWork W2926256696 @default.
- W2938291464 hasRelatedWork W2963576203 @default.
- W2938291464 hasRelatedWork W2964307722 @default.
- W2938291464 hasRelatedWork W3049278490 @default.
- W2938291464 hasRelatedWork W3196415493 @default.
- W2938291464 hasRelatedWork W3208516011 @default.
- W2938291464 isParatext "false" @default.
- W2938291464 isRetracted "false" @default.
- W2938291464 magId "2938291464" @default.
- W2938291464 workType "article" @default.