Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310697922> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4310697922 abstract "Recently, deep learning-based generative models have been introduced to generate singing voices. One approach is to predict the parametric vocoder features consisting of explicit speech parameters. This approach has the advantage that the meaning of each feature is explicitly distinguished. Another approach is to predict mel-spectrograms for a neural vocoder. However, parametric vocoders have limitations of voice quality and the mel-spectrogram features are difficult to model because the timbre and pitch information are entangled. In this study, we propose a singing voice synthesis model with multi-task learning to use both approaches -- acoustic features for a parametric vocoder and mel-spectrograms for a neural vocoder. By using the parametric vocoder features as auxiliary features, the proposed model can efficiently disentangle and control the timbre and pitch components of the mel-spectrogram. Moreover, a generative adversarial network framework is applied to improve the quality of singing voices in a multi-singer model. Experimental results demonstrate that our proposed model can generate more natural singing voices than the single-task models, while performing better than the conventional parametric vocoder-based model." @default.
- W4310697922 created "2022-12-16" @default.
- W4310697922 creator A5001941528 @default.
- W4310697922 creator A5038515968 @default.
- W4310697922 creator A5062867075 @default.
- W4310697922 date "2022-06-23" @default.
- W4310697922 modified "2023-10-03" @default.
- W4310697922 title "Adversarial Multi-Task Learning for Disentangling Timbre and Pitch in Singing Voice Synthesis" @default.
- W4310697922 doi "https://doi.org/10.48550/arxiv.2206.11558" @default.
- W4310697922 hasPublicationYear "2022" @default.
- W4310697922 type Work @default.
- W4310697922 citedByCount "0" @default.
- W4310697922 crossrefType "posted-content" @default.
- W4310697922 hasAuthorship W4310697922A5001941528 @default.
- W4310697922 hasAuthorship W4310697922A5038515968 @default.
- W4310697922 hasAuthorship W4310697922A5062867075 @default.
- W4310697922 hasBestOaLocation W43106979221 @default.
- W4310697922 hasConcept C105795698 @default.
- W4310697922 hasConcept C117251300 @default.
- W4310697922 hasConcept C121332964 @default.
- W4310697922 hasConcept C138885662 @default.
- W4310697922 hasConcept C142362112 @default.
- W4310697922 hasConcept C153349607 @default.
- W4310697922 hasConcept C154945302 @default.
- W4310697922 hasConcept C162324750 @default.
- W4310697922 hasConcept C167966045 @default.
- W4310697922 hasConcept C187736073 @default.
- W4310697922 hasConcept C24574437 @default.
- W4310697922 hasConcept C24890656 @default.
- W4310697922 hasConcept C2776401178 @default.
- W4310697922 hasConcept C2776539107 @default.
- W4310697922 hasConcept C2780451532 @default.
- W4310697922 hasConcept C28490314 @default.
- W4310697922 hasConcept C33923547 @default.
- W4310697922 hasConcept C39890363 @default.
- W4310697922 hasConcept C41008148 @default.
- W4310697922 hasConcept C41895202 @default.
- W4310697922 hasConcept C44819458 @default.
- W4310697922 hasConcept C45273575 @default.
- W4310697922 hasConcept C50644808 @default.
- W4310697922 hasConcept C558565934 @default.
- W4310697922 hasConceptScore W4310697922C105795698 @default.
- W4310697922 hasConceptScore W4310697922C117251300 @default.
- W4310697922 hasConceptScore W4310697922C121332964 @default.
- W4310697922 hasConceptScore W4310697922C138885662 @default.
- W4310697922 hasConceptScore W4310697922C142362112 @default.
- W4310697922 hasConceptScore W4310697922C153349607 @default.
- W4310697922 hasConceptScore W4310697922C154945302 @default.
- W4310697922 hasConceptScore W4310697922C162324750 @default.
- W4310697922 hasConceptScore W4310697922C167966045 @default.
- W4310697922 hasConceptScore W4310697922C187736073 @default.
- W4310697922 hasConceptScore W4310697922C24574437 @default.
- W4310697922 hasConceptScore W4310697922C24890656 @default.
- W4310697922 hasConceptScore W4310697922C2776401178 @default.
- W4310697922 hasConceptScore W4310697922C2776539107 @default.
- W4310697922 hasConceptScore W4310697922C2780451532 @default.
- W4310697922 hasConceptScore W4310697922C28490314 @default.
- W4310697922 hasConceptScore W4310697922C33923547 @default.
- W4310697922 hasConceptScore W4310697922C39890363 @default.
- W4310697922 hasConceptScore W4310697922C41008148 @default.
- W4310697922 hasConceptScore W4310697922C41895202 @default.
- W4310697922 hasConceptScore W4310697922C44819458 @default.
- W4310697922 hasConceptScore W4310697922C45273575 @default.
- W4310697922 hasConceptScore W4310697922C50644808 @default.
- W4310697922 hasConceptScore W4310697922C558565934 @default.
- W4310697922 hasLocation W43106979221 @default.
- W4310697922 hasLocation W43106979222 @default.
- W4310697922 hasOpenAccess W4310697922 @default.
- W4310697922 hasPrimaryLocation W43106979221 @default.
- W4310697922 hasRelatedWork W162634215 @default.
- W4310697922 hasRelatedWork W2107990538 @default.
- W4310697922 hasRelatedWork W2108382268 @default.
- W4310697922 hasRelatedWork W2138997758 @default.
- W4310697922 hasRelatedWork W2149825536 @default.
- W4310697922 hasRelatedWork W2152591660 @default.
- W4310697922 hasRelatedWork W2168987487 @default.
- W4310697922 hasRelatedWork W2406107460 @default.
- W4310697922 hasRelatedWork W4364857608 @default.
- W4310697922 hasRelatedWork W4372349499 @default.
- W4310697922 isParatext "false" @default.
- W4310697922 isRetracted "false" @default.
- W4310697922 workType "article" @default.