Matches in SemOpenAlex for { <https://semopenalex.org/work/W3012736254> ?p ?o ?g. }
- W3012736254 abstract "Speaker verification is an established yet challenging task in speech processing and a very vibrant research area. Recent speaker verification (SV) systems rely on deep neural networks to extract high-level embeddings which are able to characterize the users' voices. Most of the studies have investigated on improving the discriminability of the networks to extract better embeddings for performances improvement. However, only few research focus on improving the generalization. In this paper, we propose to apply the ladder network framework in the SV systems, which combines the supervised and unsupervised learning fashions. The ladder network can make the system to have better high-level embedding by balancing the trade-off to keep/discard as much useful/useless information as possible. We evaluated the framework on two state-of-the-art SV systems, d-vector and x-vector, which can be used for different use cases. The experiments showed that the proposed approach relatively improved the performance by 10% at most without adding parameters and augmented data." @default.
- W3012736254 created "2020-03-27" @default.
- W3012736254 creator A5008085254 @default.
- W3012736254 creator A5087941479 @default.
- W3012736254 date "2020-03-20" @default.
- W3012736254 modified "2023-09-27" @default.
- W3012736254 title "Improving Embedding Extraction for Speaker Verification with Ladder Network" @default.
- W3012736254 cites W1524333225 @default.
- W3012736254 cites W1538131130 @default.
- W3012736254 cites W1589137271 @default.
- W3012736254 cites W2025768430 @default.
- W3012736254 cites W2046056978 @default.
- W3012736254 cites W2072128103 @default.
- W3012736254 cites W2099797668 @default.
- W3012736254 cites W2110798204 @default.
- W3012736254 cites W2124750300 @default.
- W3012736254 cites W2136922672 @default.
- W3012736254 cites W2147062276 @default.
- W3012736254 cites W2150769028 @default.
- W3012736254 cites W2160815625 @default.
- W3012736254 cites W2395750323 @default.
- W3012736254 cites W2402144811 @default.
- W3012736254 cites W2749094483 @default.
- W3012736254 cites W2749694333 @default.
- W3012736254 cites W2790326622 @default.
- W3012736254 cites W2808631503 @default.
- W3012736254 cites W2890964092 @default.
- W3012736254 cites W2897067191 @default.
- W3012736254 cites W2962788625 @default.
- W3012736254 cites W2964121744 @default.
- W3012736254 cites W830076066 @default.
- W3012736254 cites W2889596223 @default.
- W3012736254 hasPublicationYear "2020" @default.
- W3012736254 type Work @default.
- W3012736254 sameAs 3012736254 @default.
- W3012736254 citedByCount "1" @default.
- W3012736254 countsByYear W30127362542021 @default.
- W3012736254 crossrefType "posted-content" @default.
- W3012736254 hasAuthorship W3012736254A5008085254 @default.
- W3012736254 hasAuthorship W3012736254A5087941479 @default.
- W3012736254 hasConcept C108583219 @default.
- W3012736254 hasConcept C119857082 @default.
- W3012736254 hasConcept C120665830 @default.
- W3012736254 hasConcept C121332964 @default.
- W3012736254 hasConcept C127413603 @default.
- W3012736254 hasConcept C133892786 @default.
- W3012736254 hasConcept C134306372 @default.
- W3012736254 hasConcept C154945302 @default.
- W3012736254 hasConcept C177148314 @default.
- W3012736254 hasConcept C192209626 @default.
- W3012736254 hasConcept C201995342 @default.
- W3012736254 hasConcept C2780451532 @default.
- W3012736254 hasConcept C28490314 @default.
- W3012736254 hasConcept C2982762665 @default.
- W3012736254 hasConcept C2984842247 @default.
- W3012736254 hasConcept C33923547 @default.
- W3012736254 hasConcept C41008148 @default.
- W3012736254 hasConcept C41608201 @default.
- W3012736254 hasConcept C50644808 @default.
- W3012736254 hasConceptScore W3012736254C108583219 @default.
- W3012736254 hasConceptScore W3012736254C119857082 @default.
- W3012736254 hasConceptScore W3012736254C120665830 @default.
- W3012736254 hasConceptScore W3012736254C121332964 @default.
- W3012736254 hasConceptScore W3012736254C127413603 @default.
- W3012736254 hasConceptScore W3012736254C133892786 @default.
- W3012736254 hasConceptScore W3012736254C134306372 @default.
- W3012736254 hasConceptScore W3012736254C154945302 @default.
- W3012736254 hasConceptScore W3012736254C177148314 @default.
- W3012736254 hasConceptScore W3012736254C192209626 @default.
- W3012736254 hasConceptScore W3012736254C201995342 @default.
- W3012736254 hasConceptScore W3012736254C2780451532 @default.
- W3012736254 hasConceptScore W3012736254C28490314 @default.
- W3012736254 hasConceptScore W3012736254C2982762665 @default.
- W3012736254 hasConceptScore W3012736254C2984842247 @default.
- W3012736254 hasConceptScore W3012736254C33923547 @default.
- W3012736254 hasConceptScore W3012736254C41008148 @default.
- W3012736254 hasConceptScore W3012736254C41608201 @default.
- W3012736254 hasConceptScore W3012736254C50644808 @default.
- W3012736254 hasLocation W30127362541 @default.
- W3012736254 hasOpenAccess W3012736254 @default.
- W3012736254 hasPrimaryLocation W30127362541 @default.
- W3012736254 hasRelatedWork W2234895705 @default.
- W3012736254 hasRelatedWork W2603648207 @default.
- W3012736254 hasRelatedWork W2805184146 @default.
- W3012736254 hasRelatedWork W2900969522 @default.
- W3012736254 hasRelatedWork W2922069550 @default.
- W3012736254 hasRelatedWork W2939763029 @default.
- W3012736254 hasRelatedWork W2948636084 @default.
- W3012736254 hasRelatedWork W2952904717 @default.
- W3012736254 hasRelatedWork W2954456502 @default.
- W3012736254 hasRelatedWork W3011185790 @default.
- W3012736254 hasRelatedWork W3013104201 @default.
- W3012736254 hasRelatedWork W3014419828 @default.
- W3012736254 hasRelatedWork W3015271757 @default.
- W3012736254 hasRelatedWork W3035510741 @default.
- W3012736254 hasRelatedWork W3047605943 @default.
- W3012736254 hasRelatedWork W3091985378 @default.
- W3012736254 hasRelatedWork W3103320289 @default.
- W3012736254 hasRelatedWork W3104717349 @default.
- W3012736254 hasRelatedWork W3163903701 @default.