FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100378519> ?p ?o ?g. }

• W3100378519 endingPage "479" @default.
• W3100378519 startingPage "468" @default.
• W3100378519 abstract "An effective approach for voice conversion (VC) is to disentangle linguistic content from other components in the speech signal. The effectiveness of variational autoencoder (VAE) based VC (VAE-VC), for instance, strongly relies on this principle. In our prior work, we proposed a cross-domain VAE-VC (CDVAE-VC) framework, which utilized acoustic features of different properties, to improve the performance of VAE-VC. We believed that the success came from more disentangled latent representations. In this paper, we extend the CDVAE-VC framework by incorporating the concept of adversarial learning, in order to further increase the degree of disentanglement, thereby improving the quality and similarity of converted speech. More specifically, we first investigate the effectiveness of incorporating the generative adversarial networks (GANs) with CDVAE-VC. Then, we consider the concept of domain adversarial training and add an explicit constraint to the latent representation, realized by a speaker classifier, to explicitly eliminate the speaker information that resides in the latent code. Experimental results confirm that the degree of disentanglement of the learned latent representation can be enhanced by both GANs and the speaker classifier. Meanwhile, subjective evaluation results in terms of quality and similarity scores demonstrate the effectiveness of our proposed methods." @default.
• W3100378519 created "2020-11-23" @default.
• W3100378519 creator A5000377034 @default.
• W3100378519 creator A5016009480 @default.
• W3100378519 creator A5016026582 @default.
• W3100378519 creator A5039839551 @default.
• W3100378519 creator A5044008055 @default.
• W3100378519 creator A5066130866 @default.
• W3100378519 creator A5071214181 @default.
• W3100378519 date "2020-08-01" @default.
• W3100378519 modified "2023-09-22" @default.
• W3100378519 title "Unsupervised Representation Disentanglement Using Cross Domain Features and Adversarial Learning in Variational Autoencoder Based Voice Conversion" @default.
• W3100378519 cites W1509691205 @default.
• W3100378519 cites W1599112982 @default.
• W3100378519 cites W1903029394 @default.
• W3100378519 cites W1977362459 @default.
• W3100378519 cites W2017425464 @default.
• W3100378519 cites W2022125261 @default.
• W3100378519 cites W2048646122 @default.
• W3100378519 cites W2049686551 @default.
• W3100378519 cites W2086796102 @default.
• W3100378519 cites W2093450784 @default.
• W3100378519 cites W2100819376 @default.
• W3100378519 cites W2114543868 @default.
• W3100378519 cites W2120605154 @default.
• W3100378519 cites W2121387787 @default.
• W3100378519 cites W2123003832 @default.
• W3100378519 cites W2156142001 @default.
• W3100378519 cites W2156477760 @default.
• W3100378519 cites W2157412983 @default.
• W3100378519 cites W2161476805 @default.
• W3100378519 cites W2293049663 @default.
• W3100378519 cites W2512087624 @default.
• W3100378519 cites W2518172956 @default.
• W3100378519 cites W2532494225 @default.
• W3100378519 cites W2576309025 @default.
• W3100378519 cites W2587088898 @default.
• W3100378519 cites W2666408839 @default.
• W3100378519 cites W2733416080 @default.
• W3100378519 cites W2796339975 @default.
• W3100378519 cites W2804998325 @default.
• W3100378519 cites W2889061305 @default.
• W3100378519 cites W2889064624 @default.
• W3100378519 cites W2889329491 @default.
• W3100378519 cites W2889457963 @default.
• W3100378519 cites W2903365642 @default.
• W3100378519 cites W2907262790 @default.
• W3100378519 cites W2911540263 @default.
• W3100378519 cites W2913340405 @default.
• W3100378519 cites W2937020545 @default.
• W3100378519 cites W2937579788 @default.
• W3100378519 cites W2946555236 @default.
• W3100378519 cites W2962684181 @default.
• W3100378519 cites W2963425185 @default.
• W3100378519 cites W2963539064 @default.
• W3100378519 cites W2963830550 @default.
• W3100378519 cites W2972659941 @default.
• W3100378519 cites W2972812066 @default.
• W3100378519 cites W2973135352 @default.
• W3100378519 cites W3125709657 @default.
• W3100378519 doi "https://doi.org/10.1109/tetci.2020.2977678" @default.
• W3100378519 hasPublicationYear "2020" @default.
• W3100378519 type Work @default.
• W3100378519 sameAs 3100378519 @default.
• W3100378519 citedByCount "30" @default.
• W3100378519 countsByYear W31003785192020 @default.
• W3100378519 countsByYear W31003785192021 @default.
• W3100378519 countsByYear W31003785192022 @default.
• W3100378519 countsByYear W31003785192023 @default.
• W3100378519 crossrefType "journal-article" @default.
• W3100378519 hasAuthorship W3100378519A5000377034 @default.
• W3100378519 hasAuthorship W3100378519A5016009480 @default.
• W3100378519 hasAuthorship W3100378519A5016026582 @default.
• W3100378519 hasAuthorship W3100378519A5039839551 @default.
• W3100378519 hasAuthorship W3100378519A5044008055 @default.
• W3100378519 hasAuthorship W3100378519A5066130866 @default.
• W3100378519 hasAuthorship W3100378519A5071214181 @default.
• W3100378519 hasBestOaLocation W31003785191 @default.
• W3100378519 hasConcept C101738243 @default.
• W3100378519 hasConcept C103278499 @default.
• W3100378519 hasConcept C108583219 @default.
• W3100378519 hasConcept C115961682 @default.
• W3100378519 hasConcept C153180895 @default.
• W3100378519 hasConcept C154945302 @default.
• W3100378519 hasConcept C17744445 @default.
• W3100378519 hasConcept C199539241 @default.
• W3100378519 hasConcept C2524010 @default.
• W3100378519 hasConcept C2776036281 @default.
• W3100378519 hasConcept C2776359362 @default.
• W3100378519 hasConcept C28490314 @default.
• W3100378519 hasConcept C33923547 @default.
• W3100378519 hasConcept C37736160 @default.
• W3100378519 hasConcept C39890363 @default.
• W3100378519 hasConcept C41008148 @default.
• W3100378519 hasConcept C59404180 @default.
• W3100378519 hasConcept C94625758 @default.
• W3100378519 hasConcept C95623464 @default.
• W3100378519 hasConceptScore W3100378519C101738243 @default.

• next