Matches in SemOpenAlex for { <https://semopenalex.org/work/W3016007107> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W3016007107 abstract "Singing voice conversion is to convert a singer's voice to another one's voice without changing singing content. Recent work shows that unsupervised singing voice conversion can be achieved with an autoencoder-based approach [1]. However, the converted singing voice can be easily out of key, showing that the existing approach cannot model the pitch information precisely. In this paper, we propose to advance the existing unsupervised singing voice conversion method proposed in [1] to achieve more accurate pitch translation and flexible pitch manipulation. Specifically, the proposed PitchNet added an adversarially trained pitch regression network to enforce the encoder network to learn pitch invariant phoneme representation, and a separate module to feed pitch extracted from the source audio to the decoder network. Our evaluation shows that the proposed method can greatly improve the quality of the converted singing voice (2.92 vs 3.75 in MOS). We also demonstrate that the pitch of converted singing can be easily controlled during generation by changing the levels of the extracted pitch before passing it to the decoder network." @default.
- W3016007107 created "2020-04-17" @default.
- W3016007107 creator A5009348332 @default.
- W3016007107 creator A5021176244 @default.
- W3016007107 creator A5034476404 @default.
- W3016007107 creator A5040951732 @default.
- W3016007107 creator A5063467033 @default.
- W3016007107 date "2020-05-01" @default.
- W3016007107 modified "2023-09-24" @default.
- W3016007107 title "Pitchnet: Unsupervised Singing Voice Conversion with Pitch Adversarial Network" @default.
- W3016007107 cites W2063634999 @default.
- W3016007107 cites W2067709094 @default.
- W3016007107 cites W2191779130 @default.
- W3016007107 cites W2516406502 @default.
- W3016007107 cites W2778460379 @default.
- W3016007107 cites W2972812066 @default.
- W3016007107 doi "https://doi.org/10.1109/icassp40776.2020.9054199" @default.
- W3016007107 hasPublicationYear "2020" @default.
- W3016007107 type Work @default.
- W3016007107 sameAs 3016007107 @default.
- W3016007107 citedByCount "20" @default.
- W3016007107 countsByYear W30160071072019 @default.
- W3016007107 countsByYear W30160071072020 @default.
- W3016007107 countsByYear W30160071072021 @default.
- W3016007107 countsByYear W30160071072022 @default.
- W3016007107 countsByYear W30160071072023 @default.
- W3016007107 crossrefType "proceedings-article" @default.
- W3016007107 hasAuthorship W3016007107A5009348332 @default.
- W3016007107 hasAuthorship W3016007107A5021176244 @default.
- W3016007107 hasAuthorship W3016007107A5034476404 @default.
- W3016007107 hasAuthorship W3016007107A5040951732 @default.
- W3016007107 hasAuthorship W3016007107A5063467033 @default.
- W3016007107 hasBestOaLocation W30160071072 @default.
- W3016007107 hasConcept C101738243 @default.
- W3016007107 hasConcept C111919701 @default.
- W3016007107 hasConcept C118505674 @default.
- W3016007107 hasConcept C121332964 @default.
- W3016007107 hasConcept C135622632 @default.
- W3016007107 hasConcept C154945302 @default.
- W3016007107 hasConcept C24890656 @default.
- W3016007107 hasConcept C28490314 @default.
- W3016007107 hasConcept C41008148 @default.
- W3016007107 hasConcept C44819458 @default.
- W3016007107 hasConcept C50644808 @default.
- W3016007107 hasConcept C61328038 @default.
- W3016007107 hasConceptScore W3016007107C101738243 @default.
- W3016007107 hasConceptScore W3016007107C111919701 @default.
- W3016007107 hasConceptScore W3016007107C118505674 @default.
- W3016007107 hasConceptScore W3016007107C121332964 @default.
- W3016007107 hasConceptScore W3016007107C135622632 @default.
- W3016007107 hasConceptScore W3016007107C154945302 @default.
- W3016007107 hasConceptScore W3016007107C24890656 @default.
- W3016007107 hasConceptScore W3016007107C28490314 @default.
- W3016007107 hasConceptScore W3016007107C41008148 @default.
- W3016007107 hasConceptScore W3016007107C44819458 @default.
- W3016007107 hasConceptScore W3016007107C50644808 @default.
- W3016007107 hasConceptScore W3016007107C61328038 @default.
- W3016007107 hasLocation W30160071071 @default.
- W3016007107 hasLocation W30160071072 @default.
- W3016007107 hasOpenAccess W3016007107 @default.
- W3016007107 hasPrimaryLocation W30160071071 @default.
- W3016007107 hasRelatedWork W10333054 @default.
- W3016007107 hasRelatedWork W11798771 @default.
- W3016007107 hasRelatedWork W15106243 @default.
- W3016007107 hasRelatedWork W2308727 @default.
- W3016007107 hasRelatedWork W3083127 @default.
- W3016007107 hasRelatedWork W3310707 @default.
- W3016007107 hasRelatedWork W5996824 @default.
- W3016007107 hasRelatedWork W7273074 @default.
- W3016007107 hasRelatedWork W7946549 @default.
- W3016007107 hasRelatedWork W9638664 @default.
- W3016007107 isParatext "false" @default.
- W3016007107 isRetracted "false" @default.
- W3016007107 magId "3016007107" @default.
- W3016007107 workType "article" @default.