Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224928197> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4224928197 abstract "In recognition-synthesis based any-to-one voice conversion (VC), an automatic speech recognition (ASR) model is employed to extract content-related features and a synthesizer is built to predict the acoustic features of the target speaker from the content-related features of any source speakers at the conversion stage. Since source speakers are unknown at the training stage, we have to use the content-related features of the target speaker to estimate the parameters of the synthesizer. This inconsistency between conversion and training stages constrains the speaker similarity of converted speech. To address this issue, a cyclic training method is proposed in this paper. This method designs pseudo-source acoustic features, which are generated by converting the training data of the target speaker towards multiple speakers in a reference corpus. Then, these pseudo-source acoustic features are used as the input of the synthesizer at the training stage to predict the acoustic features of the target speaker and a cyclic reconstruction loss is derived. Experimental results show that our proposed method achieved more consistent accuracy of acoustic feature prediction for various source speakers than the baseline method. It also achieved better similarity of converted speech, especially for the pairs of source and target speakers with distant speaker characteristics." @default.
- W4224928197 created "2022-04-28" @default.
- W4224928197 creator A5017296972 @default.
- W4224928197 creator A5030295554 @default.
- W4224928197 creator A5059516164 @default.
- W4224928197 creator A5059767940 @default.
- W4224928197 creator A5064657549 @default.
- W4224928197 date "2022-05-23" @default.
- W4224928197 modified "2023-10-01" @default.
- W4224928197 title "Improving Recognition-Synthesis Based any-to-one Voice Conversion with Cyclic Training" @default.
- W4224928197 cites W1509691205 @default.
- W4224928197 cites W1972420736 @default.
- W4224928197 cites W2004299580 @default.
- W4224928197 cites W2049686551 @default.
- W4224928197 cites W2100819376 @default.
- W4224928197 cites W2118154032 @default.
- W4224928197 cites W2120605154 @default.
- W4224928197 cites W2121387787 @default.
- W4224928197 cites W2126143605 @default.
- W4224928197 cites W2157412983 @default.
- W4224928197 cites W2401544731 @default.
- W4224928197 cites W2526425061 @default.
- W4224928197 cites W2532494225 @default.
- W4224928197 cites W2804998325 @default.
- W4224928197 cites W2888922217 @default.
- W4224928197 cites W2889329491 @default.
- W4224928197 cites W2902070858 @default.
- W4224928197 cites W2938583109 @default.
- W4224928197 cites W2972399707 @default.
- W4224928197 cites W3015338123 @default.
- W4224928197 cites W3097001834 @default.
- W4224928197 cites W3099078140 @default.
- W4224928197 cites W4245885054 @default.
- W4224928197 cites W4249468441 @default.
- W4224928197 doi "https://doi.org/10.1109/icassp43922.2022.9747140" @default.
- W4224928197 hasPublicationYear "2022" @default.
- W4224928197 type Work @default.
- W4224928197 citedByCount "3" @default.
- W4224928197 countsByYear W42249281972022 @default.
- W4224928197 countsByYear W42249281972023 @default.
- W4224928197 crossrefType "proceedings-article" @default.
- W4224928197 hasAuthorship W4224928197A5017296972 @default.
- W4224928197 hasAuthorship W4224928197A5030295554 @default.
- W4224928197 hasAuthorship W4224928197A5059516164 @default.
- W4224928197 hasAuthorship W4224928197A5059767940 @default.
- W4224928197 hasAuthorship W4224928197A5064657549 @default.
- W4224928197 hasConcept C103278499 @default.
- W4224928197 hasConcept C115961682 @default.
- W4224928197 hasConcept C133892786 @default.
- W4224928197 hasConcept C138885662 @default.
- W4224928197 hasConcept C14999030 @default.
- W4224928197 hasConcept C153180895 @default.
- W4224928197 hasConcept C154945302 @default.
- W4224928197 hasConcept C2776401178 @default.
- W4224928197 hasConcept C28490314 @default.
- W4224928197 hasConcept C41008148 @default.
- W4224928197 hasConcept C41895202 @default.
- W4224928197 hasConceptScore W4224928197C103278499 @default.
- W4224928197 hasConceptScore W4224928197C115961682 @default.
- W4224928197 hasConceptScore W4224928197C133892786 @default.
- W4224928197 hasConceptScore W4224928197C138885662 @default.
- W4224928197 hasConceptScore W4224928197C14999030 @default.
- W4224928197 hasConceptScore W4224928197C153180895 @default.
- W4224928197 hasConceptScore W4224928197C154945302 @default.
- W4224928197 hasConceptScore W4224928197C2776401178 @default.
- W4224928197 hasConceptScore W4224928197C28490314 @default.
- W4224928197 hasConceptScore W4224928197C41008148 @default.
- W4224928197 hasConceptScore W4224928197C41895202 @default.
- W4224928197 hasFunder F4320330944 @default.
- W4224928197 hasLocation W42249281971 @default.
- W4224928197 hasOpenAccess W4224928197 @default.
- W4224928197 hasPrimaryLocation W42249281971 @default.
- W4224928197 hasRelatedWork W1524014603 @default.
- W4224928197 hasRelatedWork W2015538044 @default.
- W4224928197 hasRelatedWork W2016461833 @default.
- W4224928197 hasRelatedWork W2052253960 @default.
- W4224928197 hasRelatedWork W2382607599 @default.
- W4224928197 hasRelatedWork W2760085659 @default.
- W4224928197 hasRelatedWork W2893763841 @default.
- W4224928197 hasRelatedWork W2929240682 @default.
- W4224928197 hasRelatedWork W3197541072 @default.
- W4224928197 hasRelatedWork W2480412556 @default.
- W4224928197 isParatext "false" @default.
- W4224928197 isRetracted "false" @default.
- W4224928197 workType "article" @default.