FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2946555236> ?p ?o ?g. }

• W2946555236 endingPage "1443" @default.
• W2946555236 startingPage "1432" @default.
• W2946555236 abstract "This paper proposes a non-parallel voice conversion (VC) method using a variant of the conditional variational autoencoder (VAE) called an auxiliary classifier VAE. The proposed method has two key features. First, it adopts fully convolutional architectures to construct the encoder and decoder networks so that the networks can learn conversion rules that capture the time dependencies in the acoustic feature sequences of source and target speech. Second, it uses information-theoretic regularization for the model training to ensure that the information in the attribute class label will not be lost in the conversion process. With regular conditional VAEs, the encoder and decoder are free to ignore the attribute class label input. This can be problematic since in such a situation, the attribute class label will have little effect on controlling the voice characteristics of input speech at test time. Such situations can be avoided by introducing an auxiliary classifier and training the encoder and decoder so that the attribute classes of the decoder outputs are correctly predicted by the classifier. We also present several ways to convert the feature sequence of input speech using the trained encoder and decoder and compare them in terms of audio quality through objective and subjective evaluations. We confirmed experimentally that the proposed method outperformed baseline non-parallel VC systems and performed comparably to an open-source parallel VC system trained using a parallel corpus in a speaker identity conversion task." @default.
• W2946555236 created "2019-05-29" @default.
• W2946555236 creator A5001243214 @default.
• W2946555236 creator A5002179552 @default.
• W2946555236 creator A5020693766 @default.
• W2946555236 creator A5079710814 @default.
• W2946555236 date "2019-09-01" @default.
• W2946555236 modified "2023-10-18" @default.
• W2946555236 title "ACVAE-VC: Non-Parallel Voice Conversion With Auxiliary Classifier Variational Autoencoder" @default.
• W2946555236 cites W1509691205 @default.
• W2946555236 cites W1974745215 @default.
• W2946555236 cites W1977362459 @default.
• W2946555236 cites W2022125261 @default.
• W2946555236 cites W2041448063 @default.
• W2946555236 cites W2056852181 @default.
• W2946555236 cites W2057609679 @default.
• W2946555236 cites W2086796102 @default.
• W2946555236 cites W2093450784 @default.
• W2946555236 cites W2105160541 @default.
• W2946555236 cites W2120605154 @default.
• W2946555236 cites W2123003832 @default.
• W2946555236 cites W2123771434 @default.
• W2946555236 cites W2127520494 @default.
• W2946555236 cites W2142300631 @default.
• W2946555236 cites W2148846882 @default.
• W2946555236 cites W2150769028 @default.
• W2946555236 cites W2156142001 @default.
• W2946555236 cites W2157412983 @default.
• W2946555236 cites W2161727827 @default.
• W2946555236 cites W2293049663 @default.
• W2946555236 cites W2471520273 @default.
• W2946555236 cites W2515020857 @default.
• W2946555236 cites W2518312472 @default.
• W2946555236 cites W2532494225 @default.
• W2946555236 cites W2651834199 @default.
• W2946555236 cites W2747744257 @default.
• W2946555236 cites W2749651610 @default.
• W2946555236 cites W2804998325 @default.
• W2946555236 cites W2811001736 @default.
• W2946555236 cites W2889329491 @default.
• W2946555236 cites W2890983311 @default.
• W2946555236 cites W2902070858 @default.
• W2946555236 cites W2911708970 @default.
• W2946555236 cites W2962793481 @default.
• W2946555236 cites W2962896155 @default.
• W2946555236 cites W2963035245 @default.
• W2946555236 cites W2963175743 @default.
• W2946555236 cites W2963300588 @default.
• W2946555236 cites W2963444790 @default.
• W2946555236 cites W2963539064 @default.
• W2946555236 doi "https://doi.org/10.1109/taslp.2019.2917232" @default.
• W2946555236 hasPublicationYear "2019" @default.
• W2946555236 type Work @default.
• W2946555236 sameAs 2946555236 @default.
• W2946555236 citedByCount "71" @default.
• W2946555236 countsByYear W29465552362018 @default.
• W2946555236 countsByYear W29465552362019 @default.
• W2946555236 countsByYear W29465552362020 @default.
• W2946555236 countsByYear W29465552362021 @default.
• W2946555236 countsByYear W29465552362022 @default.
• W2946555236 countsByYear W29465552362023 @default.
• W2946555236 crossrefType "journal-article" @default.
• W2946555236 hasAuthorship W2946555236A5001243214 @default.
• W2946555236 hasAuthorship W2946555236A5002179552 @default.
• W2946555236 hasAuthorship W2946555236A5020693766 @default.
• W2946555236 hasAuthorship W2946555236A5079710814 @default.
• W2946555236 hasConcept C101738243 @default.
• W2946555236 hasConcept C108583219 @default.
• W2946555236 hasConcept C111919701 @default.
• W2946555236 hasConcept C118505674 @default.
• W2946555236 hasConcept C153180895 @default.
• W2946555236 hasConcept C154945302 @default.
• W2946555236 hasConcept C28490314 @default.
• W2946555236 hasConcept C41008148 @default.
• W2946555236 hasConcept C95623464 @default.
• W2946555236 hasConceptScore W2946555236C101738243 @default.
• W2946555236 hasConceptScore W2946555236C108583219 @default.
• W2946555236 hasConceptScore W2946555236C111919701 @default.
• W2946555236 hasConceptScore W2946555236C118505674 @default.
• W2946555236 hasConceptScore W2946555236C153180895 @default.
• W2946555236 hasConceptScore W2946555236C154945302 @default.
• W2946555236 hasConceptScore W2946555236C28490314 @default.
• W2946555236 hasConceptScore W2946555236C41008148 @default.
• W2946555236 hasConceptScore W2946555236C95623464 @default.
• W2946555236 hasIssue "9" @default.
• W2946555236 hasLocation W29465552361 @default.
• W2946555236 hasOpenAccess W2946555236 @default.
• W2946555236 hasPrimaryLocation W29465552361 @default.
• W2946555236 hasRelatedWork W2292254049 @default.
• W2946555236 hasRelatedWork W2592385986 @default.
• W2946555236 hasRelatedWork W2610906757 @default.
• W2946555236 hasRelatedWork W2772780115 @default.
• W2946555236 hasRelatedWork W2897995864 @default.
• W2946555236 hasRelatedWork W2998168123 @default.
• W2946555236 hasRelatedWork W3032998101 @default.
• W2946555236 hasRelatedWork W3099179464 @default.
• W2946555236 hasRelatedWork W4281924768 @default.
• W2946555236 hasRelatedWork W4287995534 @default.

• next