Matches in SemOpenAlex for { <https://semopenalex.org/work/W2000513720> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2000513720 endingPage "824" @default.
- W2000513720 startingPage "816" @default.
- W2000513720 abstract "This paper describes a novel parameter generation algorithm for an HMM-based speech synthesis technique. The conventional algorithm generates a parameter trajectory of static features that maximizes the likelihood of a given HMM for the parameter sequence consisting of the static and dynamic features under an explicit constraint between those two features. The generated trajectory is often excessively smoothed due to the statistical processing. Using the over-smoothed speech parameters usually causes muffled sounds. In order to alleviate the over-smoothing effect, we propose a generation algorithm considering not only the HMM likelihood maximized in the conventional algorithm but also a likelihood for a global variance (GV) of the generated trajectory. The latter likelihood works as a penalty for the over-smoothing, i.e., a reduction of the GV of the generated trajectory. The result of a perceptual evaluation demonstrates that the proposed algorithm causes considerably large improvements in the naturalness of synthetic speech." @default.
- W2000513720 created "2016-06-24" @default.
- W2000513720 creator A5050450986 @default.
- W2000513720 creator A5078330211 @default.
- W2000513720 date "2007-05-01" @default.
- W2000513720 modified "2023-10-06" @default.
- W2000513720 title "A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis" @default.
- W2000513720 cites W1512429158 @default.
- W2000513720 cites W1563645159 @default.
- W2000513720 cites W1600722501 @default.
- W2000513720 cites W1935012542 @default.
- W2000513720 cites W1963627370 @default.
- W2000513720 cites W2013887835 @default.
- W2000513720 cites W2049686551 @default.
- W2000513720 cites W2066452495 @default.
- W2000513720 cites W2093094447 @default.
- W2000513720 cites W2093450784 @default.
- W2000513720 cites W2095134692 @default.
- W2000513720 cites W2096980176 @default.
- W2000513720 cites W2114659828 @default.
- W2000513720 cites W2115040572 @default.
- W2000513720 cites W2116669443 @default.
- W2000513720 cites W2119174565 @default.
- W2000513720 cites W2129082420 @default.
- W2000513720 cites W2150658333 @default.
- W2000513720 cites W2154280657 @default.
- W2000513720 cites W2154920538 @default.
- W2000513720 cites W2166823384 @default.
- W2000513720 cites W22889032 @default.
- W2000513720 cites W2337335398 @default.
- W2000513720 cites W234770729 @default.
- W2000513720 cites W2394921947 @default.
- W2000513720 cites W33683307 @default.
- W2000513720 cites W344150399 @default.
- W2000513720 cites W42451021 @default.
- W2000513720 cites W564913581 @default.
- W2000513720 cites W77890607 @default.
- W2000513720 cites W2531982967 @default.
- W2000513720 doi "https://doi.org/10.1093/ietisy/e90-d.5.816" @default.
- W2000513720 hasPublicationYear "2007" @default.
- W2000513720 type Work @default.
- W2000513720 sameAs 2000513720 @default.
- W2000513720 citedByCount "327" @default.
- W2000513720 countsByYear W20005137202012 @default.
- W2000513720 countsByYear W20005137202013 @default.
- W2000513720 countsByYear W20005137202014 @default.
- W2000513720 countsByYear W20005137202015 @default.
- W2000513720 countsByYear W20005137202016 @default.
- W2000513720 countsByYear W20005137202017 @default.
- W2000513720 countsByYear W20005137202018 @default.
- W2000513720 countsByYear W20005137202019 @default.
- W2000513720 countsByYear W20005137202020 @default.
- W2000513720 countsByYear W20005137202021 @default.
- W2000513720 countsByYear W20005137202022 @default.
- W2000513720 countsByYear W20005137202023 @default.
- W2000513720 crossrefType "journal-article" @default.
- W2000513720 hasAuthorship W2000513720A5050450986 @default.
- W2000513720 hasAuthorship W2000513720A5078330211 @default.
- W2000513720 hasConcept C11413529 @default.
- W2000513720 hasConcept C121955636 @default.
- W2000513720 hasConcept C144133560 @default.
- W2000513720 hasConcept C14999030 @default.
- W2000513720 hasConcept C154945302 @default.
- W2000513720 hasConcept C196083921 @default.
- W2000513720 hasConcept C23224414 @default.
- W2000513720 hasConcept C28490314 @default.
- W2000513720 hasConcept C41008148 @default.
- W2000513720 hasConceptScore W2000513720C11413529 @default.
- W2000513720 hasConceptScore W2000513720C121955636 @default.
- W2000513720 hasConceptScore W2000513720C144133560 @default.
- W2000513720 hasConceptScore W2000513720C14999030 @default.
- W2000513720 hasConceptScore W2000513720C154945302 @default.
- W2000513720 hasConceptScore W2000513720C196083921 @default.
- W2000513720 hasConceptScore W2000513720C23224414 @default.
- W2000513720 hasConceptScore W2000513720C28490314 @default.
- W2000513720 hasConceptScore W2000513720C41008148 @default.
- W2000513720 hasIssue "5" @default.
- W2000513720 hasLocation W20005137201 @default.
- W2000513720 hasOpenAccess W2000513720 @default.
- W2000513720 hasPrimaryLocation W20005137201 @default.
- W2000513720 hasRelatedWork W155946340 @default.
- W2000513720 hasRelatedWork W1589081167 @default.
- W2000513720 hasRelatedWork W2038801705 @default.
- W2000513720 hasRelatedWork W2110108310 @default.
- W2000513720 hasRelatedWork W2174199565 @default.
- W2000513720 hasRelatedWork W2181773877 @default.
- W2000513720 hasRelatedWork W2290770594 @default.
- W2000513720 hasRelatedWork W2579204149 @default.
- W2000513720 hasRelatedWork W2904846757 @default.
- W2000513720 hasRelatedWork W2968379855 @default.
- W2000513720 hasVolume "E90-D" @default.
- W2000513720 isParatext "false" @default.
- W2000513720 isRetracted "false" @default.
- W2000513720 magId "2000513720" @default.
- W2000513720 workType "article" @default.