Matches in SemOpenAlex for { <https://semopenalex.org/work/W2994715919> ?p ?o ?g. }
- W2994715919 abstract "We introduce a novel sequence-to-sequence (seq2seq) voice conversion (VC) model based on the Transformer architecture with text-to-speech (TTS) pretraining. Seq2seq VC models are attractive owing to their ability to convert prosody. While seq2seq models based on recurrent neural networks (RNNs) and convolutional neural networks (CNNs) have been successfully applied to VC, the use of the Transformer network, which has shown promising results in various speech processing tasks, has not yet been investigated. Nonetheless, their data-hungry property and the mispronunciation of converted speech make seq2seq models far from practical. To this end, we propose a simple yet effective pretraining technique to transfer knowledge from learned TTS models, which benefit from large-scale, easily accessible TTS corpora. VC models initialized with such pretrained model parameters are able to generate effective hidden representations for high-fidelity, highly intelligible converted speech. Experimental results show that such a pretraining scheme can facilitate data-efficient training and outperform an RNN-based seq2seq VC model in terms of intelligibility, naturalness, and similarity." @default.
- W2994715919 created "2019-12-26" @default.
- W2994715919 creator A5000377034 @default.
- W2994715919 creator A5001243214 @default.
- W2994715919 creator A5037001032 @default.
- W2994715919 creator A5078330211 @default.
- W2994715919 creator A5078778981 @default.
- W2994715919 date "2019-12-14" @default.
- W2994715919 modified "2023-09-23" @default.
- W2994715919 title "Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining" @default.
- W2994715919 cites W1494198834 @default.
- W2994715919 cites W1902237438 @default.
- W2994715919 cites W2049686551 @default.
- W2994715919 cites W2120605154 @default.
- W2994715919 cites W2130942839 @default.
- W2994715919 cites W2156142001 @default.
- W2994715919 cites W2471520273 @default.
- W2994715919 cites W2749651610 @default.
- W2994715919 cites W2767052532 @default.
- W2994715919 cites W2786868129 @default.
- W2994715919 cites W2889329491 @default.
- W2994715919 cites W2892009249 @default.
- W2994715919 cites W2899877258 @default.
- W2994715919 cites W2901254300 @default.
- W2994715919 cites W2901607128 @default.
- W2994715919 cites W2903739847 @default.
- W2994715919 cites W2949382160 @default.
- W2994715919 cites W2959758584 @default.
- W2994715919 cites W2962780374 @default.
- W2994715919 cites W2963192573 @default.
- W2994715919 cites W2963403868 @default.
- W2994715919 cites W2963432880 @default.
- W2994715919 cites W2963609956 @default.
- W2994715919 cites W2963808252 @default.
- W2994715919 cites W2963912924 @default.
- W2994715919 cites W2964243274 @default.
- W2994715919 cites W2964265128 @default.
- W2994715919 cites W2964308564 @default.
- W2994715919 cites W2972818416 @default.
- W2994715919 cites W2972970915 @default.
- W2994715919 cites W2972999331 @default.
- W2994715919 cites W2973142754 @default.
- W2994715919 cites W2978099976 @default.
- W2994715919 cites W2982055294 @default.
- W2994715919 cites W3006777338 @default.
- W2994715919 cites W3015338123 @default.
- W2994715919 cites W3034420534 @default.
- W2994715919 cites W3099078140 @default.
- W2994715919 cites W3101689408 @default.
- W2994715919 cites W95152782 @default.
- W2994715919 doi "https://doi.org/10.48550/arxiv.1912.06813" @default.
- W2994715919 hasPublicationYear "2019" @default.
- W2994715919 type Work @default.
- W2994715919 sameAs 2994715919 @default.
- W2994715919 citedByCount "26" @default.
- W2994715919 countsByYear W29947159192020 @default.
- W2994715919 countsByYear W29947159192021 @default.
- W2994715919 countsByYear W29947159192022 @default.
- W2994715919 crossrefType "posted-content" @default.
- W2994715919 hasAuthorship W2994715919A5000377034 @default.
- W2994715919 hasAuthorship W2994715919A5001243214 @default.
- W2994715919 hasAuthorship W2994715919A5037001032 @default.
- W2994715919 hasAuthorship W2994715919A5078330211 @default.
- W2994715919 hasAuthorship W2994715919A5078778981 @default.
- W2994715919 hasBestOaLocation W29947159191 @default.
- W2994715919 hasConcept C111472728 @default.
- W2994715919 hasConcept C113364801 @default.
- W2994715919 hasConcept C119599485 @default.
- W2994715919 hasConcept C121332964 @default.
- W2994715919 hasConcept C127413603 @default.
- W2994715919 hasConcept C134537474 @default.
- W2994715919 hasConcept C138885662 @default.
- W2994715919 hasConcept C147168706 @default.
- W2994715919 hasConcept C14999030 @default.
- W2994715919 hasConcept C154945302 @default.
- W2994715919 hasConcept C165801399 @default.
- W2994715919 hasConcept C28490314 @default.
- W2994715919 hasConcept C41008148 @default.
- W2994715919 hasConcept C50644808 @default.
- W2994715919 hasConcept C542774811 @default.
- W2994715919 hasConcept C60048801 @default.
- W2994715919 hasConcept C62520636 @default.
- W2994715919 hasConcept C66322947 @default.
- W2994715919 hasConceptScore W2994715919C111472728 @default.
- W2994715919 hasConceptScore W2994715919C113364801 @default.
- W2994715919 hasConceptScore W2994715919C119599485 @default.
- W2994715919 hasConceptScore W2994715919C121332964 @default.
- W2994715919 hasConceptScore W2994715919C127413603 @default.
- W2994715919 hasConceptScore W2994715919C134537474 @default.
- W2994715919 hasConceptScore W2994715919C138885662 @default.
- W2994715919 hasConceptScore W2994715919C147168706 @default.
- W2994715919 hasConceptScore W2994715919C14999030 @default.
- W2994715919 hasConceptScore W2994715919C154945302 @default.
- W2994715919 hasConceptScore W2994715919C165801399 @default.
- W2994715919 hasConceptScore W2994715919C28490314 @default.
- W2994715919 hasConceptScore W2994715919C41008148 @default.
- W2994715919 hasConceptScore W2994715919C50644808 @default.
- W2994715919 hasConceptScore W2994715919C542774811 @default.
- W2994715919 hasConceptScore W2994715919C60048801 @default.
- W2994715919 hasConceptScore W2994715919C62520636 @default.