Matches in SemOpenAlex for { <https://semopenalex.org/work/W2106632010> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2106632010 abstract "A minimum generation error (MGE) criterion had been proposed for model training in HMM-based speech synthesis. In this paper, we apply the MGE criterion to model adaptation for HMM-based speech synthesis, and introduce an MGE linear regression (MGELR) based model adaptation algorithm, where the regression matrices used to transform source models are optimized so as to minimize the generation errors of adaptation data. In addition, we incorporate the recent improvements of MGE criterion into MGELR-based model adaptation, including state alignment under MGE criterion and using a log spectral distortion (LSD) instead of Euclidean distance for spectral distortion measure. From the experimental results, the adaptation performance was improved after incorporating these two techniques, and the formal listening tests showed that the quality and speaker similarity of synthesized speech after MGELRbased adaptation were significantly improved over the original MLLR-based adaptation. Index Terms: Speech synthesis, HMM, speaker adaptation, minimum generation error, linear regression" @default.
- W2106632010 created "2016-06-24" @default.
- W2106632010 creator A5039492028 @default.
- W2106632010 creator A5050450986 @default.
- W2106632010 creator A5064290493 @default.
- W2106632010 date "2009-09-06" @default.
- W2106632010 modified "2023-09-27" @default.
- W2106632010 title "An improved minimum generation error based model adaptation for HMM-based speech synthesis" @default.
- W2106632010 cites W129217914 @default.
- W2106632010 cites W1600722501 @default.
- W2106632010 cites W1602430027 @default.
- W2106632010 cites W2002342963 @default.
- W2106632010 cites W2010581677 @default.
- W2106632010 cites W2049686551 @default.
- W2106632010 cites W2111194146 @default.
- W2106632010 cites W2146871184 @default.
- W2106632010 cites W2158942523 @default.
- W2106632010 cites W2165856656 @default.
- W2106632010 cites W2166823384 @default.
- W2106632010 cites W233059834 @default.
- W2106632010 cites W3036802551 @default.
- W2106632010 cites W330074099 @default.
- W2106632010 doi "https://doi.org/10.21437/interspeech.2009-150" @default.
- W2106632010 hasPublicationYear "2009" @default.
- W2106632010 type Work @default.
- W2106632010 sameAs 2106632010 @default.
- W2106632010 citedByCount "5" @default.
- W2106632010 countsByYear W21066320102012 @default.
- W2106632010 countsByYear W21066320102014 @default.
- W2106632010 countsByYear W21066320102016 @default.
- W2106632010 crossrefType "proceedings-article" @default.
- W2106632010 hasAuthorship W2106632010A5039492028 @default.
- W2106632010 hasAuthorship W2106632010A5050450986 @default.
- W2106632010 hasAuthorship W2106632010A5064290493 @default.
- W2106632010 hasConcept C11413529 @default.
- W2106632010 hasConcept C120174047 @default.
- W2106632010 hasConcept C120665830 @default.
- W2106632010 hasConcept C121332964 @default.
- W2106632010 hasConcept C126780896 @default.
- W2106632010 hasConcept C139807058 @default.
- W2106632010 hasConcept C14999030 @default.
- W2106632010 hasConcept C153180895 @default.
- W2106632010 hasConcept C154945302 @default.
- W2106632010 hasConcept C194257627 @default.
- W2106632010 hasConcept C23224414 @default.
- W2106632010 hasConcept C2776257435 @default.
- W2106632010 hasConcept C28490314 @default.
- W2106632010 hasConcept C31258907 @default.
- W2106632010 hasConcept C41008148 @default.
- W2106632010 hasConceptScore W2106632010C11413529 @default.
- W2106632010 hasConceptScore W2106632010C120174047 @default.
- W2106632010 hasConceptScore W2106632010C120665830 @default.
- W2106632010 hasConceptScore W2106632010C121332964 @default.
- W2106632010 hasConceptScore W2106632010C126780896 @default.
- W2106632010 hasConceptScore W2106632010C139807058 @default.
- W2106632010 hasConceptScore W2106632010C14999030 @default.
- W2106632010 hasConceptScore W2106632010C153180895 @default.
- W2106632010 hasConceptScore W2106632010C154945302 @default.
- W2106632010 hasConceptScore W2106632010C194257627 @default.
- W2106632010 hasConceptScore W2106632010C23224414 @default.
- W2106632010 hasConceptScore W2106632010C2776257435 @default.
- W2106632010 hasConceptScore W2106632010C28490314 @default.
- W2106632010 hasConceptScore W2106632010C31258907 @default.
- W2106632010 hasConceptScore W2106632010C41008148 @default.
- W2106632010 hasLocation W21066320101 @default.
- W2106632010 hasOpenAccess W2106632010 @default.
- W2106632010 hasPrimaryLocation W21066320101 @default.
- W2106632010 hasRelatedWork W1486800612 @default.
- W2106632010 hasRelatedWork W1511242468 @default.
- W2106632010 hasRelatedWork W1823291590 @default.
- W2106632010 hasRelatedWork W1989010196 @default.
- W2106632010 hasRelatedWork W2006654546 @default.
- W2106632010 hasRelatedWork W2007243334 @default.
- W2106632010 hasRelatedWork W2059701405 @default.
- W2106632010 hasRelatedWork W2096075540 @default.
- W2106632010 hasRelatedWork W2102867314 @default.
- W2106632010 hasRelatedWork W2104233551 @default.
- W2106632010 hasRelatedWork W2106208939 @default.
- W2106632010 hasRelatedWork W2107908983 @default.
- W2106632010 hasRelatedWork W2111194146 @default.
- W2106632010 hasRelatedWork W2126483088 @default.
- W2106632010 hasRelatedWork W2153914468 @default.
- W2106632010 hasRelatedWork W2156453709 @default.
- W2106632010 hasRelatedWork W2163246542 @default.
- W2106632010 hasRelatedWork W233059834 @default.
- W2106632010 hasRelatedWork W2405545977 @default.
- W2106632010 hasRelatedWork W2605492095 @default.
- W2106632010 isParatext "false" @default.
- W2106632010 isRetracted "false" @default.
- W2106632010 magId "2106632010" @default.
- W2106632010 workType "article" @default.