Matches in SemOpenAlex for { <https://semopenalex.org/work/W3108360147> ?p ?o ?g. }
- W3108360147 abstract "Recent neural vocoders usually use a WaveNet-like network to capture the long-term dependencies of the waveform, but a large number of parameters are required to obtain good modeling capabilities. In this paper, an efficient network, named location-variable convolution, is proposed to model the dependencies of waveforms. Different from the use of unified convolution kernels in WaveNet to capture the dependencies of arbitrary waveforms, location-variable convolutions utilizes a kernel predictor to generate multiple sets of convolution kernels based on the mel-spectrum, where each set of convolution kernels is used to perform convolution operations on the associated waveform intervals. Combining WaveGlow and location-variable convolutions, an efficient vocoder, named MelGlow, is designed. Experiments on the LJSpeech dataset show that MelGlow achieves better performance than WaveGlow at small model sizes, which verifies the effectiveness and potential optimization space of location-variable convolutions." @default.
- W3108360147 created "2020-12-07" @default.
- W3108360147 creator A5016038454 @default.
- W3108360147 creator A5026912956 @default.
- W3108360147 creator A5074472751 @default.
- W3108360147 creator A5084554132 @default.
- W3108360147 date "2020-12-02" @default.
- W3108360147 modified "2023-09-27" @default.
- W3108360147 title "MelGlow: Efficient Waveform Generative Network Based on Location-Variable Convolution" @default.
- W3108360147 cites W1836465849 @default.
- W3108360147 cites W1966264494 @default.
- W3108360147 cites W2097645910 @default.
- W3108360147 cites W2099471712 @default.
- W3108360147 cites W2120847449 @default.
- W3108360147 cites W2151409182 @default.
- W3108360147 cites W2471520273 @default.
- W3108360147 cites W2587284713 @default.
- W3108360147 cites W2766812927 @default.
- W3108360147 cites W2901997113 @default.
- W3108360147 cites W2903739847 @default.
- W3108360147 cites W2949382160 @default.
- W3108360147 cites W2951418500 @default.
- W3108360147 cites W2955616469 @default.
- W3108360147 cites W2962882868 @default.
- W3108360147 cites W2963090522 @default.
- W3108360147 cites W2963091184 @default.
- W3108360147 cites W2963300588 @default.
- W3108360147 cites W2963609956 @default.
- W3108360147 cites W2963782041 @default.
- W3108360147 cites W2963975282 @default.
- W3108360147 cites W2964121744 @default.
- W3108360147 cites W2964243274 @default.
- W3108360147 cites W2964307104 @default.
- W3108360147 cites W2970006822 @default.
- W3108360147 cites W2970730223 @default.
- W3108360147 cites W2972333964 @default.
- W3108360147 cites W2972789651 @default.
- W3108360147 cites W2996286887 @default.
- W3108360147 cites W3015338123 @default.
- W3108360147 cites W3015611309 @default.
- W3108360147 cites W3015878662 @default.
- W3108360147 cites W3035083561 @default.
- W3108360147 cites W3097795905 @default.
- W3108360147 doi "https://doi.org/10.48550/arxiv.2012.01684" @default.
- W3108360147 hasPublicationYear "2020" @default.
- W3108360147 type Work @default.
- W3108360147 sameAs 3108360147 @default.
- W3108360147 citedByCount "1" @default.
- W3108360147 countsByYear W31083601472021 @default.
- W3108360147 crossrefType "posted-content" @default.
- W3108360147 hasAuthorship W3108360147A5016038454 @default.
- W3108360147 hasAuthorship W3108360147A5026912956 @default.
- W3108360147 hasAuthorship W3108360147A5074472751 @default.
- W3108360147 hasAuthorship W3108360147A5084554132 @default.
- W3108360147 hasBestOaLocation W31083601471 @default.
- W3108360147 hasConcept C102519508 @default.
- W3108360147 hasConcept C11413529 @default.
- W3108360147 hasConcept C114614502 @default.
- W3108360147 hasConcept C134306372 @default.
- W3108360147 hasConcept C153180895 @default.
- W3108360147 hasConcept C154945302 @default.
- W3108360147 hasConcept C177264268 @default.
- W3108360147 hasConcept C182365436 @default.
- W3108360147 hasConcept C194980680 @default.
- W3108360147 hasConcept C197424946 @default.
- W3108360147 hasConcept C199360897 @default.
- W3108360147 hasConcept C203024314 @default.
- W3108360147 hasConcept C33923547 @default.
- W3108360147 hasConcept C41008148 @default.
- W3108360147 hasConcept C45347329 @default.
- W3108360147 hasConcept C50644808 @default.
- W3108360147 hasConcept C554190296 @default.
- W3108360147 hasConcept C74193536 @default.
- W3108360147 hasConcept C76155785 @default.
- W3108360147 hasConcept C76563020 @default.
- W3108360147 hasConceptScore W3108360147C102519508 @default.
- W3108360147 hasConceptScore W3108360147C11413529 @default.
- W3108360147 hasConceptScore W3108360147C114614502 @default.
- W3108360147 hasConceptScore W3108360147C134306372 @default.
- W3108360147 hasConceptScore W3108360147C153180895 @default.
- W3108360147 hasConceptScore W3108360147C154945302 @default.
- W3108360147 hasConceptScore W3108360147C177264268 @default.
- W3108360147 hasConceptScore W3108360147C182365436 @default.
- W3108360147 hasConceptScore W3108360147C194980680 @default.
- W3108360147 hasConceptScore W3108360147C197424946 @default.
- W3108360147 hasConceptScore W3108360147C199360897 @default.
- W3108360147 hasConceptScore W3108360147C203024314 @default.
- W3108360147 hasConceptScore W3108360147C33923547 @default.
- W3108360147 hasConceptScore W3108360147C41008148 @default.
- W3108360147 hasConceptScore W3108360147C45347329 @default.
- W3108360147 hasConceptScore W3108360147C50644808 @default.
- W3108360147 hasConceptScore W3108360147C554190296 @default.
- W3108360147 hasConceptScore W3108360147C74193536 @default.
- W3108360147 hasConceptScore W3108360147C76155785 @default.
- W3108360147 hasConceptScore W3108360147C76563020 @default.
- W3108360147 hasLocation W31083601471 @default.
- W3108360147 hasOpenAccess W3108360147 @default.
- W3108360147 hasPrimaryLocation W31083601471 @default.
- W3108360147 hasRelatedWork W2100852738 @default.
- W3108360147 hasRelatedWork W2110459882 @default.