Matches in SemOpenAlex for { <https://semopenalex.org/work/W228314209> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W228314209 abstract "This paper proposes a method to detect the errors in synthetic speech of a unit selection speech synthesis system automatically using log likelihood ratio and support vector machine (SVM). For SVM training, a set of synthetic speech are firstly generated by a given speech synthesis system and their synthetic errors are labeled by manually annotating the segments that sound unnatural. Then, two context-dependent acoustic models are trained using the natural and unnatural segments of labeled synthetic speech respectively. The log likelihood ratio of acoustic features between these two models is adopted to train the SVM classifier for error detection. Experimental results show the proposed method is effective in detecting the errors of pitch contour within a word for a Mandarin speech synthesis system. The proposed SVM method using log likelihood ratio between context-dependent acoustic models outperforms the SVM classifier trained on acoustic features directly." @default.
- W228314209 created "2016-06-24" @default.
- W228314209 creator A5004733344 @default.
- W228314209 creator A5009348332 @default.
- W228314209 creator A5050660824 @default.
- W228314209 creator A5057227915 @default.
- W228314209 creator A5059767940 @default.
- W228314209 date "2010-09-26" @default.
- W228314209 modified "2023-10-08" @default.
- W228314209 title "Automatic error detection for unit selection speech synthesis using log likelihood ratio based SVM classifier" @default.
- W228314209 cites W103312509 @default.
- W228314209 cites W1600722501 @default.
- W228314209 cites W1935012542 @default.
- W228314209 cites W1963627370 @default.
- W228314209 cites W1965555277 @default.
- W228314209 cites W1973766695 @default.
- W228314209 cites W2008834750 @default.
- W228314209 cites W2089959702 @default.
- W228314209 cites W2091359957 @default.
- W228314209 cites W2127172428 @default.
- W228314209 cites W2150658333 @default.
- W228314209 cites W2166823384 @default.
- W228314209 cites W2404765346 @default.
- W228314209 cites W3142087749 @default.
- W228314209 cites W564913581 @default.
- W228314209 doi "https://doi.org/10.21437/interspeech.2010-75" @default.
- W228314209 hasPublicationYear "2010" @default.
- W228314209 type Work @default.
- W228314209 sameAs 228314209 @default.
- W228314209 citedByCount "11" @default.
- W228314209 countsByYear W2283142092012 @default.
- W228314209 countsByYear W2283142092013 @default.
- W228314209 countsByYear W2283142092014 @default.
- W228314209 countsByYear W2283142092016 @default.
- W228314209 countsByYear W2283142092017 @default.
- W228314209 crossrefType "proceedings-article" @default.
- W228314209 hasAuthorship W228314209A5004733344 @default.
- W228314209 hasAuthorship W228314209A5009348332 @default.
- W228314209 hasAuthorship W228314209A5050660824 @default.
- W228314209 hasAuthorship W228314209A5057227915 @default.
- W228314209 hasAuthorship W228314209A5059767940 @default.
- W228314209 hasConcept C12267149 @default.
- W228314209 hasConcept C14999030 @default.
- W228314209 hasConcept C153180895 @default.
- W228314209 hasConcept C154945302 @default.
- W228314209 hasConcept C28490314 @default.
- W228314209 hasConcept C41008148 @default.
- W228314209 hasConcept C95623464 @default.
- W228314209 hasConceptScore W228314209C12267149 @default.
- W228314209 hasConceptScore W228314209C14999030 @default.
- W228314209 hasConceptScore W228314209C153180895 @default.
- W228314209 hasConceptScore W228314209C154945302 @default.
- W228314209 hasConceptScore W228314209C28490314 @default.
- W228314209 hasConceptScore W228314209C41008148 @default.
- W228314209 hasConceptScore W228314209C95623464 @default.
- W228314209 hasLocation W2283142091 @default.
- W228314209 hasOpenAccess W228314209 @default.
- W228314209 hasPrimaryLocation W2283142091 @default.
- W228314209 hasRelatedWork W1544395264 @default.
- W228314209 hasRelatedWork W172917546 @default.
- W228314209 hasRelatedWork W2008834750 @default.
- W228314209 hasRelatedWork W2109862664 @default.
- W228314209 hasRelatedWork W2143657265 @default.
- W228314209 hasRelatedWork W2144556654 @default.
- W228314209 hasRelatedWork W2150658333 @default.
- W228314209 hasRelatedWork W2171700247 @default.
- W228314209 hasRelatedWork W2524154163 @default.
- W228314209 hasRelatedWork W2534837439 @default.
- W228314209 hasRelatedWork W2739017883 @default.
- W228314209 hasRelatedWork W27410839 @default.
- W228314209 hasRelatedWork W3001745422 @default.
- W228314209 hasRelatedWork W3144582766 @default.
- W228314209 hasRelatedWork W2184675439 @default.
- W228314209 hasRelatedWork W2406597179 @default.
- W228314209 hasRelatedWork W2759749073 @default.
- W228314209 hasRelatedWork W2823545936 @default.
- W228314209 hasRelatedWork W2872501382 @default.
- W228314209 hasRelatedWork W3113761592 @default.
- W228314209 isParatext "false" @default.
- W228314209 isRetracted "false" @default.
- W228314209 magId "228314209" @default.
- W228314209 workType "article" @default.