Matches in SemOpenAlex for { <https://semopenalex.org/work/W3093669695> ?p ?o ?g. }
- W3093669695 abstract "The neural network (NN) based singing voice synthesis (SVS) systems require sufficient data to train well and are prone to over-fitting due to data scarcity. However, we often encounter data limitation problem in building SVS systems because of high data acquisition and annotation costs. In this work, we propose a Perceptual Entropy (PE) loss derived from a psycho-acoustic hearing model to regularize the network. With a one-hour open-source singing voice database, we explore the impact of the PE loss on various mainstream sequence-to-sequence models, including the RNN-based, transformer-based, and conformer-based models. Our experiments show that the PE loss can mitigate the over-fitting problem and significantly improve the synthesized singing quality reflected in objective and subjective evaluations." @default.
- W3093669695 created "2020-10-29" @default.
- W3093669695 creator A5008336983 @default.
- W3093669695 creator A5009985839 @default.
- W3093669695 creator A5071652041 @default.
- W3093669695 creator A5074415592 @default.
- W3093669695 creator A5075115977 @default.
- W3093669695 date "2020-10-22" @default.
- W3093669695 modified "2023-10-16" @default.
- W3093669695 title "Sequence-to-sequence Singing Voice Synthesis with Perceptual Entropy Loss" @default.
- W3093669695 cites W1525613233 @default.
- W3093669695 cites W2058097301 @default.
- W3093669695 cites W2096588881 @default.
- W3093669695 cites W2124097505 @default.
- W3093669695 cites W2128301448 @default.
- W3093669695 cites W2144520790 @default.
- W3093669695 cites W2408435475 @default.
- W3093669695 cites W2515336442 @default.
- W3093669695 cites W2516406502 @default.
- W3093669695 cites W2778460379 @default.
- W3093669695 cites W2795247881 @default.
- W3093669695 cites W2889244839 @default.
- W3093669695 cites W2921576841 @default.
- W3093669695 cites W2937242376 @default.
- W3093669695 cites W2940405045 @default.
- W3093669695 cites W2963403868 @default.
- W3093669695 cites W2963970792 @default.
- W3093669695 cites W29794711 @default.
- W3093669695 cites W2984106626 @default.
- W3093669695 cites W2994986888 @default.
- W3093669695 cites W2995005087 @default.
- W3093669695 cites W2995670387 @default.
- W3093669695 cites W3015499232 @default.
- W3093669695 cites W3015516707 @default.
- W3093669695 cites W3015645837 @default.
- W3093669695 cites W3019084079 @default.
- W3093669695 cites W3025165719 @default.
- W3093669695 cites W3035430139 @default.
- W3093669695 cites W3048084370 @default.
- W3093669695 cites W3048092838 @default.
- W3093669695 cites W3081279708 @default.
- W3093669695 cites W3082910224 @default.
- W3093669695 doi "https://doi.org/10.48550/arxiv.2010.12024" @default.
- W3093669695 hasPublicationYear "2020" @default.
- W3093669695 type Work @default.
- W3093669695 sameAs 3093669695 @default.
- W3093669695 citedByCount "0" @default.
- W3093669695 crossrefType "posted-content" @default.
- W3093669695 hasAuthorship W3093669695A5008336983 @default.
- W3093669695 hasAuthorship W3093669695A5009985839 @default.
- W3093669695 hasAuthorship W3093669695A5071652041 @default.
- W3093669695 hasAuthorship W3093669695A5074415592 @default.
- W3093669695 hasAuthorship W3093669695A5075115977 @default.
- W3093669695 hasBestOaLocation W30936696951 @default.
- W3093669695 hasConcept C119599485 @default.
- W3093669695 hasConcept C121332964 @default.
- W3093669695 hasConcept C127413603 @default.
- W3093669695 hasConcept C147168706 @default.
- W3093669695 hasConcept C154945302 @default.
- W3093669695 hasConcept C15744967 @default.
- W3093669695 hasConcept C165801399 @default.
- W3093669695 hasConcept C169760540 @default.
- W3093669695 hasConcept C24890656 @default.
- W3093669695 hasConcept C26760741 @default.
- W3093669695 hasConcept C2778112365 @default.
- W3093669695 hasConcept C28490314 @default.
- W3093669695 hasConcept C41008148 @default.
- W3093669695 hasConcept C44819458 @default.
- W3093669695 hasConcept C50644808 @default.
- W3093669695 hasConcept C54355233 @default.
- W3093669695 hasConcept C66322947 @default.
- W3093669695 hasConcept C86803240 @default.
- W3093669695 hasConceptScore W3093669695C119599485 @default.
- W3093669695 hasConceptScore W3093669695C121332964 @default.
- W3093669695 hasConceptScore W3093669695C127413603 @default.
- W3093669695 hasConceptScore W3093669695C147168706 @default.
- W3093669695 hasConceptScore W3093669695C154945302 @default.
- W3093669695 hasConceptScore W3093669695C15744967 @default.
- W3093669695 hasConceptScore W3093669695C165801399 @default.
- W3093669695 hasConceptScore W3093669695C169760540 @default.
- W3093669695 hasConceptScore W3093669695C24890656 @default.
- W3093669695 hasConceptScore W3093669695C26760741 @default.
- W3093669695 hasConceptScore W3093669695C2778112365 @default.
- W3093669695 hasConceptScore W3093669695C28490314 @default.
- W3093669695 hasConceptScore W3093669695C41008148 @default.
- W3093669695 hasConceptScore W3093669695C44819458 @default.
- W3093669695 hasConceptScore W3093669695C50644808 @default.
- W3093669695 hasConceptScore W3093669695C54355233 @default.
- W3093669695 hasConceptScore W3093669695C66322947 @default.
- W3093669695 hasConceptScore W3093669695C86803240 @default.
- W3093669695 hasLocation W30936696951 @default.
- W3093669695 hasOpenAccess W3093669695 @default.
- W3093669695 hasPrimaryLocation W30936696951 @default.
- W3093669695 hasRelatedWork W1583001605 @default.
- W3093669695 hasRelatedWork W2329734087 @default.
- W3093669695 hasRelatedWork W2921857201 @default.
- W3093669695 hasRelatedWork W2932319787 @default.
- W3093669695 hasRelatedWork W2950161879 @default.
- W3093669695 hasRelatedWork W2951961943 @default.
- W3093669695 hasRelatedWork W2972910332 @default.