Matches in SemOpenAlex for { <https://semopenalex.org/work/W3014794275> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3014794275 abstract "With the pervasiveness of voice control on smart devices, speaker verification is widely used as the preferred identity authentication mechanism due to its convenience. However, the task of in-the-wild speaker verification is challenging, considering the speech samples may contain lots of identity-unrelated information, e.g., background noise, reverberation, emotion, etc. Previous works focus on optimizing the model to improve verification accuracy, without considering eliminating the impact from the identity-unrelated information. To solve this problem, we propose SEF-ALDR, a novel Speaker Embedding Framework via Adversarial Learning based Disentangled Representation, to further improve the performance of existing models on speaker verification. The key idea is to retrieve as much speaker identity information as possible from the original speech, i.e., minimizing the impact of identity-unrelated information on the speaker verification task. We utilize the adversarial learning method to train an eliminating encoder that produces an embedding without speaker identity representation. Hence, the speaker identity information can be well preserved in the complementary features that are not used by the eliminating encoder in the original speech. Experimental results demonstrate that the proposed framework can significantly improve the performance of the speaker verification by 20.3% and 28.7% on average over 13 tested baselines on dataset Voxceleb1 and 9 tested baselines on dataset Voxceleb2 respectively, without adjusting the structure or hyper-parameters of them. Furthermore, porting an existing model into the proposed framework is straightforward and cost-efficient, with very little effort from the model owners due to the modular design of the framework." @default.
- W3014794275 created "2020-04-10" @default.
- W3014794275 creator A5001764975 @default.
- W3014794275 creator A5014477100 @default.
- W3014794275 creator A5015456692 @default.
- W3014794275 creator A5027504758 @default.
- W3014794275 creator A5035471714 @default.
- W3014794275 date "2019-11-27" @default.
- W3014794275 modified "2023-09-23" @default.
- W3014794275 title "SEF-ALDR: A Speaker Embedding Framework via Adversarial Learning based Disentangled Representation" @default.
- W3014794275 hasPublicationYear "2019" @default.
- W3014794275 type Work @default.
- W3014794275 sameAs 3014794275 @default.
- W3014794275 citedByCount "1" @default.
- W3014794275 countsByYear W30147942752020 @default.
- W3014794275 crossrefType "posted-content" @default.
- W3014794275 hasAuthorship W3014794275A5001764975 @default.
- W3014794275 hasAuthorship W3014794275A5014477100 @default.
- W3014794275 hasAuthorship W3014794275A5015456692 @default.
- W3014794275 hasAuthorship W3014794275A5027504758 @default.
- W3014794275 hasAuthorship W3014794275A5035471714 @default.
- W3014794275 hasConcept C111919701 @default.
- W3014794275 hasConcept C118505674 @default.
- W3014794275 hasConcept C120665830 @default.
- W3014794275 hasConcept C121332964 @default.
- W3014794275 hasConcept C133892786 @default.
- W3014794275 hasConcept C149838564 @default.
- W3014794275 hasConcept C154945302 @default.
- W3014794275 hasConcept C162324750 @default.
- W3014794275 hasConcept C17744445 @default.
- W3014794275 hasConcept C187736073 @default.
- W3014794275 hasConcept C192209626 @default.
- W3014794275 hasConcept C199539241 @default.
- W3014794275 hasConcept C24890656 @default.
- W3014794275 hasConcept C2776359362 @default.
- W3014794275 hasConcept C2778355321 @default.
- W3014794275 hasConcept C2780451532 @default.
- W3014794275 hasConcept C28490314 @default.
- W3014794275 hasConcept C37736160 @default.
- W3014794275 hasConcept C41008148 @default.
- W3014794275 hasConcept C41608201 @default.
- W3014794275 hasConcept C94625758 @default.
- W3014794275 hasConceptScore W3014794275C111919701 @default.
- W3014794275 hasConceptScore W3014794275C118505674 @default.
- W3014794275 hasConceptScore W3014794275C120665830 @default.
- W3014794275 hasConceptScore W3014794275C121332964 @default.
- W3014794275 hasConceptScore W3014794275C133892786 @default.
- W3014794275 hasConceptScore W3014794275C149838564 @default.
- W3014794275 hasConceptScore W3014794275C154945302 @default.
- W3014794275 hasConceptScore W3014794275C162324750 @default.
- W3014794275 hasConceptScore W3014794275C17744445 @default.
- W3014794275 hasConceptScore W3014794275C187736073 @default.
- W3014794275 hasConceptScore W3014794275C192209626 @default.
- W3014794275 hasConceptScore W3014794275C199539241 @default.
- W3014794275 hasConceptScore W3014794275C24890656 @default.
- W3014794275 hasConceptScore W3014794275C2776359362 @default.
- W3014794275 hasConceptScore W3014794275C2778355321 @default.
- W3014794275 hasConceptScore W3014794275C2780451532 @default.
- W3014794275 hasConceptScore W3014794275C28490314 @default.
- W3014794275 hasConceptScore W3014794275C37736160 @default.
- W3014794275 hasConceptScore W3014794275C41008148 @default.
- W3014794275 hasConceptScore W3014794275C41608201 @default.
- W3014794275 hasConceptScore W3014794275C94625758 @default.
- W3014794275 hasLocation W30147942751 @default.
- W3014794275 hasOpenAccess W3014794275 @default.
- W3014794275 hasPrimaryLocation W30147942751 @default.
- W3014794275 hasRelatedWork W2099797668 @default.
- W3014794275 hasRelatedWork W2124667332 @default.
- W3014794275 hasRelatedWork W2332932830 @default.
- W3014794275 hasRelatedWork W2339276216 @default.
- W3014794275 hasRelatedWork W2790216641 @default.
- W3014794275 hasRelatedWork W2889226978 @default.
- W3014794275 hasRelatedWork W2900161882 @default.
- W3014794275 hasRelatedWork W2901368553 @default.
- W3014794275 hasRelatedWork W292968312 @default.
- W3014794275 hasRelatedWork W3008911072 @default.
- W3014794275 hasRelatedWork W3016048045 @default.
- W3014794275 hasRelatedWork W3046796449 @default.
- W3014794275 hasRelatedWork W3046954891 @default.
- W3014794275 hasRelatedWork W3096918678 @default.
- W3014794275 hasRelatedWork W3111060610 @default.
- W3014794275 hasRelatedWork W3120856754 @default.
- W3014794275 hasRelatedWork W3163829335 @default.
- W3014794275 hasRelatedWork W3163929126 @default.
- W3014794275 hasRelatedWork W3201363892 @default.
- W3014794275 hasRelatedWork W3211614993 @default.
- W3014794275 isParatext "false" @default.
- W3014794275 isRetracted "false" @default.
- W3014794275 magId "3014794275" @default.
- W3014794275 workType "article" @default.