Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224925626> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4224925626 abstract "This paper proposes a high-speed neural vocoder for CPU implementation. Two approaches for speeding up autoregressive neural vocoders have been proposed, 1) simultaneous multiple sample generation and 2) subband signal-based vocoder; so far they have been employed independently. Our neural vocoder is extremely fast as it generates multiple samples of subband signals simultaneously. Although there is an association between each subband signal, the conventional subband-based vocoder can degrade quality because each subband signal is generated from an independent probability distribution. To overcome this problem, we also introduce waveform generation that takes account of the association of each subband by employing multivariate Gaussian. Experiments show that 1) our proposed method is 1.81 times as fast as the conventional subband WaveRNN on a single-threaded CPU; 2) it outperformed the conventional method in a subjective evaluation in terms of naturalness, and achieved a mean opinion score (MOS) of 4.08 on text-to-speech task." @default.
- W4224925626 created "2022-04-28" @default.
- W4224925626 creator A5068604686 @default.
- W4224925626 creator A5076754533 @default.
- W4224925626 date "2022-05-23" @default.
- W4224925626 modified "2023-09-28" @default.
- W4224925626 title "Multi-Sample Subband Wavernn Via Multivariate Gaussian" @default.
- W4224925626 cites W2165700458 @default.
- W4224925626 cites W2172065531 @default.
- W4224925626 cites W2767052532 @default.
- W4224925626 cites W2963091184 @default.
- W4224925626 cites W2963300588 @default.
- W4224925626 cites W2964243274 @default.
- W4224925626 cites W2984862052 @default.
- W4224925626 cites W3015338123 @default.
- W4224925626 cites W3015347659 @default.
- W4224925626 cites W3096702751 @default.
- W4224925626 cites W3097538987 @default.
- W4224925626 cites W3144035034 @default.
- W4224925626 doi "https://doi.org/10.1109/icassp43922.2022.9747898" @default.
- W4224925626 hasPublicationYear "2022" @default.
- W4224925626 type Work @default.
- W4224925626 citedByCount "2" @default.
- W4224925626 countsByYear W42249256262023 @default.
- W4224925626 crossrefType "proceedings-article" @default.
- W4224925626 hasAuthorship W4224925626A5068604686 @default.
- W4224925626 hasAuthorship W4224925626A5076754533 @default.
- W4224925626 hasConcept C105795698 @default.
- W4224925626 hasConcept C119857082 @default.
- W4224925626 hasConcept C121332964 @default.
- W4224925626 hasConcept C134537474 @default.
- W4224925626 hasConcept C153180895 @default.
- W4224925626 hasConcept C154945302 @default.
- W4224925626 hasConcept C159877910 @default.
- W4224925626 hasConcept C161584116 @default.
- W4224925626 hasConcept C163716315 @default.
- W4224925626 hasConcept C185592680 @default.
- W4224925626 hasConcept C197424946 @default.
- W4224925626 hasConcept C198531522 @default.
- W4224925626 hasConcept C199360897 @default.
- W4224925626 hasConcept C2779843651 @default.
- W4224925626 hasConcept C28490314 @default.
- W4224925626 hasConcept C33923547 @default.
- W4224925626 hasConcept C41008148 @default.
- W4224925626 hasConcept C43617362 @default.
- W4224925626 hasConcept C50644808 @default.
- W4224925626 hasConcept C554190296 @default.
- W4224925626 hasConcept C62520636 @default.
- W4224925626 hasConcept C76155785 @default.
- W4224925626 hasConceptScore W4224925626C105795698 @default.
- W4224925626 hasConceptScore W4224925626C119857082 @default.
- W4224925626 hasConceptScore W4224925626C121332964 @default.
- W4224925626 hasConceptScore W4224925626C134537474 @default.
- W4224925626 hasConceptScore W4224925626C153180895 @default.
- W4224925626 hasConceptScore W4224925626C154945302 @default.
- W4224925626 hasConceptScore W4224925626C159877910 @default.
- W4224925626 hasConceptScore W4224925626C161584116 @default.
- W4224925626 hasConceptScore W4224925626C163716315 @default.
- W4224925626 hasConceptScore W4224925626C185592680 @default.
- W4224925626 hasConceptScore W4224925626C197424946 @default.
- W4224925626 hasConceptScore W4224925626C198531522 @default.
- W4224925626 hasConceptScore W4224925626C199360897 @default.
- W4224925626 hasConceptScore W4224925626C2779843651 @default.
- W4224925626 hasConceptScore W4224925626C28490314 @default.
- W4224925626 hasConceptScore W4224925626C33923547 @default.
- W4224925626 hasConceptScore W4224925626C41008148 @default.
- W4224925626 hasConceptScore W4224925626C43617362 @default.
- W4224925626 hasConceptScore W4224925626C50644808 @default.
- W4224925626 hasConceptScore W4224925626C554190296 @default.
- W4224925626 hasConceptScore W4224925626C62520636 @default.
- W4224925626 hasConceptScore W4224925626C76155785 @default.
- W4224925626 hasLocation W42249256261 @default.
- W4224925626 hasOpenAccess W4224925626 @default.
- W4224925626 hasPrimaryLocation W42249256261 @default.
- W4224925626 hasRelatedWork W10581632 @default.
- W4224925626 hasRelatedWork W11208178 @default.
- W4224925626 hasRelatedWork W11512698 @default.
- W4224925626 hasRelatedWork W11879186 @default.
- W4224925626 hasRelatedWork W13112433 @default.
- W4224925626 hasRelatedWork W1692833 @default.
- W4224925626 hasRelatedWork W5708970 @default.
- W4224925626 hasRelatedWork W637621 @default.
- W4224925626 hasRelatedWork W6479125 @default.
- W4224925626 hasRelatedWork W4036335 @default.
- W4224925626 isParatext "false" @default.
- W4224925626 isRetracted "false" @default.
- W4224925626 workType "article" @default.