Matches in SemOpenAlex for { <https://semopenalex.org/work/W3114691655> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3114691655 abstract "This paper introduces Taco-VC, a novel architecture for voice conversion based on Tacotron synthesizer, which is a sequence-to-sequence with attention model. The training of multi-speaker voice conversion systems requires a large number of resources, both in training and corpus size. Taco-VC is implemented using a single speaker Tacotron synthesizer based on Phonetic PosteriorGrams (PPGs) and a single speaker WaveNet vocoder conditioned on mel spectrograms. To enhance the converted speech quality, and to overcome over-smoothing, the outputs of Tacotron are passed through a novel speech-enhancement network, which is composed of a combination of the phoneme recognition and Tacotron networks. Our system is trained just with a single speaker corpus and adapts to new speakers using only a few minutes of training data. Using mid-size public datasets, our method outperforms the baseline in the VCC 2018 SPOKE non-parallel voice conversion task and achieves competitive results compared to multi-speaker networks trained on large private datasets." @default.
- W3114691655 created "2021-01-05" @default.
- W3114691655 creator A5072571599 @default.
- W3114691655 creator A5084602071 @default.
- W3114691655 date "2021-01-24" @default.
- W3114691655 modified "2023-09-23" @default.
- W3114691655 title "Taco-VC: A Single Speaker Tacotron based Voice Conversion with Limited Data" @default.
- W3114691655 cites W1509691205 @default.
- W3114691655 cites W2086796102 @default.
- W3114691655 cites W2107878631 @default.
- W3114691655 cites W2120605154 @default.
- W3114691655 cites W2156142001 @default.
- W3114691655 cites W2518172956 @default.
- W3114691655 cites W2739735615 @default.
- W3114691655 cites W2746474733 @default.
- W3114691655 cites W2749196786 @default.
- W3114691655 cites W2800289214 @default.
- W3114691655 cites W2802935216 @default.
- W3114691655 cites W2804998325 @default.
- W3114691655 cites W2888932932 @default.
- W3114691655 cites W2889064624 @default.
- W3114691655 cites W2889329491 @default.
- W3114691655 cites W2902070858 @default.
- W3114691655 cites W2946555236 @default.
- W3114691655 cites W2963035245 @default.
- W3114691655 cites W2963103134 @default.
- W3114691655 cites W2963403664 @default.
- W3114691655 cites W2963609956 @default.
- W3114691655 cites W2963971656 @default.
- W3114691655 cites W2964243274 @default.
- W3114691655 cites W2972970915 @default.
- W3114691655 cites W2972999331 @default.
- W3114691655 cites W3099078140 @default.
- W3114691655 doi "https://doi.org/10.23919/eusipco47968.2020.9287448" @default.
- W3114691655 hasPublicationYear "2021" @default.
- W3114691655 type Work @default.
- W3114691655 sameAs 3114691655 @default.
- W3114691655 citedByCount "5" @default.
- W3114691655 countsByYear W31146916552020 @default.
- W3114691655 countsByYear W31146916552021 @default.
- W3114691655 countsByYear W31146916552022 @default.
- W3114691655 crossrefType "proceedings-article" @default.
- W3114691655 hasAuthorship W3114691655A5072571599 @default.
- W3114691655 hasAuthorship W3114691655A5084602071 @default.
- W3114691655 hasBestOaLocation W31146916552 @default.
- W3114691655 hasConcept C127413603 @default.
- W3114691655 hasConcept C14999030 @default.
- W3114691655 hasConcept C154945302 @default.
- W3114691655 hasConcept C201995342 @default.
- W3114691655 hasConcept C2780451532 @default.
- W3114691655 hasConcept C28490314 @default.
- W3114691655 hasConcept C31972630 @default.
- W3114691655 hasConcept C3770464 @default.
- W3114691655 hasConcept C41008148 @default.
- W3114691655 hasConcept C45273575 @default.
- W3114691655 hasConceptScore W3114691655C127413603 @default.
- W3114691655 hasConceptScore W3114691655C14999030 @default.
- W3114691655 hasConceptScore W3114691655C154945302 @default.
- W3114691655 hasConceptScore W3114691655C201995342 @default.
- W3114691655 hasConceptScore W3114691655C2780451532 @default.
- W3114691655 hasConceptScore W3114691655C28490314 @default.
- W3114691655 hasConceptScore W3114691655C31972630 @default.
- W3114691655 hasConceptScore W3114691655C3770464 @default.
- W3114691655 hasConceptScore W3114691655C41008148 @default.
- W3114691655 hasConceptScore W3114691655C45273575 @default.
- W3114691655 hasLocation W31146916551 @default.
- W3114691655 hasLocation W31146916552 @default.
- W3114691655 hasOpenAccess W3114691655 @default.
- W3114691655 hasPrimaryLocation W31146916551 @default.
- W3114691655 hasRelatedWork W2029523276 @default.
- W3114691655 hasRelatedWork W2117676474 @default.
- W3114691655 hasRelatedWork W2388979876 @default.
- W3114691655 hasRelatedWork W2921059071 @default.
- W3114691655 hasRelatedWork W2946200149 @default.
- W3114691655 hasRelatedWork W2970730223 @default.
- W3114691655 hasRelatedWork W3127598333 @default.
- W3114691655 hasRelatedWork W3203164699 @default.
- W3114691655 hasRelatedWork W4310471687 @default.
- W3114691655 hasRelatedWork W4312706341 @default.
- W3114691655 isParatext "false" @default.
- W3114691655 isRetracted "false" @default.
- W3114691655 magId "3114691655" @default.
- W3114691655 workType "article" @default.