Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964351684> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2964351684 abstract "Recently, several end-to-end speaker verification systems based on deep neural networks (DNNs) have been proposed. These systems have been proven to be competitive for text-dependent tasks as well as for text-independent tasks with short utterances. However, for text-independent tasks with longer utterances, end-to-end systems are still outperformed by standard i-vector + PLDA systems. In this work, we develop an end-to-end speaker verification system that is initialized to mimic an i-vector + PLDA baseline. The system is then further trained in an end-to-end manner but regularized so that it does not deviate too far from the initial system. In this way we mitigate overfitting which normally limits the performance of end-to-end systems. The proposed system outperforms the i-vector + PLDA baseline on both long and short duration utterances." @default.
- W2964351684 created "2019-07-30" @default.
- W2964351684 creator A5035162271 @default.
- W2964351684 creator A5043239262 @default.
- W2964351684 creator A5043410084 @default.
- W2964351684 creator A5054608556 @default.
- W2964351684 creator A5060856690 @default.
- W2964351684 creator A5076315361 @default.
- W2964351684 date "2018-04-01" @default.
- W2964351684 modified "2023-09-24" @default.
- W2964351684 title "End-to-End DNN Based Speaker Recognition Inspired by I-Vector and PLDA" @default.
- W2964351684 cites W1020150683 @default.
- W2964351684 cites W1990942610 @default.
- W2964351684 cites W2039057510 @default.
- W2964351684 cites W2041823554 @default.
- W2964351684 cites W2046056978 @default.
- W2964351684 cites W2114925438 @default.
- W2964351684 cites W2150769028 @default.
- W2964351684 cites W2167136086 @default.
- W2964351684 cites W2491474862 @default.
- W2964351684 cites W2584329820 @default.
- W2964351684 cites W2587150483 @default.
- W2964351684 cites W2747476845 @default.
- W2964351684 cites W2748488820 @default.
- W2964351684 doi "https://doi.org/10.1109/icassp.2018.8461958" @default.
- W2964351684 hasPublicationYear "2018" @default.
- W2964351684 type Work @default.
- W2964351684 sameAs 2964351684 @default.
- W2964351684 citedByCount "35" @default.
- W2964351684 countsByYear W29643516842018 @default.
- W2964351684 countsByYear W29643516842019 @default.
- W2964351684 countsByYear W29643516842020 @default.
- W2964351684 countsByYear W29643516842021 @default.
- W2964351684 countsByYear W29643516842022 @default.
- W2964351684 countsByYear W29643516842023 @default.
- W2964351684 crossrefType "proceedings-article" @default.
- W2964351684 hasAuthorship W2964351684A5035162271 @default.
- W2964351684 hasAuthorship W2964351684A5043239262 @default.
- W2964351684 hasAuthorship W2964351684A5043410084 @default.
- W2964351684 hasAuthorship W2964351684A5054608556 @default.
- W2964351684 hasAuthorship W2964351684A5060856690 @default.
- W2964351684 hasAuthorship W2964351684A5076315361 @default.
- W2964351684 hasBestOaLocation W29643516842 @default.
- W2964351684 hasConcept C111368507 @default.
- W2964351684 hasConcept C12725497 @default.
- W2964351684 hasConcept C127313418 @default.
- W2964351684 hasConcept C133892786 @default.
- W2964351684 hasConcept C153180895 @default.
- W2964351684 hasConcept C154945302 @default.
- W2964351684 hasConcept C22019652 @default.
- W2964351684 hasConcept C28490314 @default.
- W2964351684 hasConcept C2982762665 @default.
- W2964351684 hasConcept C41008148 @default.
- W2964351684 hasConcept C50644808 @default.
- W2964351684 hasConcept C74296488 @default.
- W2964351684 hasConceptScore W2964351684C111368507 @default.
- W2964351684 hasConceptScore W2964351684C12725497 @default.
- W2964351684 hasConceptScore W2964351684C127313418 @default.
- W2964351684 hasConceptScore W2964351684C133892786 @default.
- W2964351684 hasConceptScore W2964351684C153180895 @default.
- W2964351684 hasConceptScore W2964351684C154945302 @default.
- W2964351684 hasConceptScore W2964351684C22019652 @default.
- W2964351684 hasConceptScore W2964351684C28490314 @default.
- W2964351684 hasConceptScore W2964351684C2982762665 @default.
- W2964351684 hasConceptScore W2964351684C41008148 @default.
- W2964351684 hasConceptScore W2964351684C50644808 @default.
- W2964351684 hasConceptScore W2964351684C74296488 @default.
- W2964351684 hasLocation W29643516841 @default.
- W2964351684 hasLocation W29643516842 @default.
- W2964351684 hasOpenAccess W2964351684 @default.
- W2964351684 hasPrimaryLocation W29643516841 @default.
- W2964351684 hasRelatedWork W2150532155 @default.
- W2964351684 hasRelatedWork W2742991909 @default.
- W2964351684 hasRelatedWork W2767651786 @default.
- W2964351684 hasRelatedWork W3015923889 @default.
- W2964351684 hasRelatedWork W3017138616 @default.
- W2964351684 hasRelatedWork W3114320604 @default.
- W2964351684 hasRelatedWork W3197533300 @default.
- W2964351684 hasRelatedWork W3201363892 @default.
- W2964351684 hasRelatedWork W4288323920 @default.
- W2964351684 hasRelatedWork W4321153309 @default.
- W2964351684 isParatext "false" @default.
- W2964351684 isRetracted "false" @default.
- W2964351684 magId "2964351684" @default.
- W2964351684 workType "article" @default.