Matches in SemOpenAlex for { <https://semopenalex.org/work/W2105160541> ?p ?o ?g. }
- W2105160541 endingPage "921" @default.
- W2105160541 startingPage "912" @default.
- W2105160541 abstract "Voice conversion can be formulated as finding a mapping function which transforms the features of the source speaker to those of the target speaker. Gaussian mixture model (GMM)-based conversion is commonly used, but it is subject to overfitting. In this paper, we propose to use partial least squares (PLS)-based transforms in voice conversion. To prevent overfitting, the degrees of freedom in the mapping can be controlled by choosing a suitable number of components. We propose a technique to combine PLS with GMMs, enabling the use of multiple local linear mappings. To further improve the perceptual quality of the mapping where rapid transitions between GMM components produce audible artefacts, we propose to low-pass filter the component posterior probabilities. The conducted experiments show that the proposed technique results in better subjective and objective quality than the baseline joint density GMM approach. In speech quality conversion preference tests, the proposed method achieved 67% preference score against the smoothed joint density GMM method and 84% preference score against the unsmoothed joint density GMM method. In objective tests the proposed method produced a lower Mel-cepstral distortion than the reference methods." @default.
- W2105160541 created "2016-06-24" @default.
- W2105160541 creator A5007583477 @default.
- W2105160541 creator A5014011829 @default.
- W2105160541 creator A5042260991 @default.
- W2105160541 creator A5049691461 @default.
- W2105160541 date "2010-07-01" @default.
- W2105160541 modified "2023-10-11" @default.
- W2105160541 title "Voice Conversion Using Partial Least Squares Regression" @default.
- W2105160541 cites W142801778 @default.
- W2105160541 cites W1927394876 @default.
- W2105160541 cites W1949974402 @default.
- W2105160541 cites W1976251851 @default.
- W2105160541 cites W1991402032 @default.
- W2105160541 cites W2005580838 @default.
- W2105160541 cites W2007023536 @default.
- W2105160541 cites W2049686551 @default.
- W2105160541 cites W2076118331 @default.
- W2105160541 cites W2099952057 @default.
- W2105160541 cites W2105698384 @default.
- W2105160541 cites W2108601574 @default.
- W2105160541 cites W2112390707 @default.
- W2105160541 cites W2118850452 @default.
- W2105160541 cites W2120605154 @default.
- W2105160541 cites W2121178298 @default.
- W2105160541 cites W2123003832 @default.
- W2105160541 cites W2130362963 @default.
- W2105160541 cites W2147152002 @default.
- W2105160541 cites W2153057929 @default.
- W2105160541 cites W2153425803 @default.
- W2105160541 cites W2153914468 @default.
- W2105160541 cites W2156142001 @default.
- W2105160541 cites W2158942523 @default.
- W2105160541 cites W2165108269 @default.
- W2105160541 cites W95300890 @default.
- W2105160541 doi "https://doi.org/10.1109/tasl.2010.2041699" @default.
- W2105160541 hasPublicationYear "2010" @default.
- W2105160541 type Work @default.
- W2105160541 sameAs 2105160541 @default.
- W2105160541 citedByCount "196" @default.
- W2105160541 countsByYear W21051605412012 @default.
- W2105160541 countsByYear W21051605412013 @default.
- W2105160541 countsByYear W21051605412014 @default.
- W2105160541 countsByYear W21051605412015 @default.
- W2105160541 countsByYear W21051605412016 @default.
- W2105160541 countsByYear W21051605412017 @default.
- W2105160541 countsByYear W21051605412018 @default.
- W2105160541 countsByYear W21051605412019 @default.
- W2105160541 countsByYear W21051605412020 @default.
- W2105160541 countsByYear W21051605412021 @default.
- W2105160541 countsByYear W21051605412022 @default.
- W2105160541 countsByYear W21051605412023 @default.
- W2105160541 crossrefType "journal-article" @default.
- W2105160541 hasAuthorship W2105160541A5007583477 @default.
- W2105160541 hasAuthorship W2105160541A5014011829 @default.
- W2105160541 hasAuthorship W2105160541A5042260991 @default.
- W2105160541 hasAuthorship W2105160541A5049691461 @default.
- W2105160541 hasConcept C119857082 @default.
- W2105160541 hasConcept C126780896 @default.
- W2105160541 hasConcept C153180895 @default.
- W2105160541 hasConcept C154945302 @default.
- W2105160541 hasConcept C194257627 @default.
- W2105160541 hasConcept C22019652 @default.
- W2105160541 hasConcept C22354355 @default.
- W2105160541 hasConcept C2776257435 @default.
- W2105160541 hasConcept C28490314 @default.
- W2105160541 hasConcept C31258907 @default.
- W2105160541 hasConcept C33923547 @default.
- W2105160541 hasConcept C41008148 @default.
- W2105160541 hasConcept C50644808 @default.
- W2105160541 hasConcept C61224824 @default.
- W2105160541 hasConceptScore W2105160541C119857082 @default.
- W2105160541 hasConceptScore W2105160541C126780896 @default.
- W2105160541 hasConceptScore W2105160541C153180895 @default.
- W2105160541 hasConceptScore W2105160541C154945302 @default.
- W2105160541 hasConceptScore W2105160541C194257627 @default.
- W2105160541 hasConceptScore W2105160541C22019652 @default.
- W2105160541 hasConceptScore W2105160541C22354355 @default.
- W2105160541 hasConceptScore W2105160541C2776257435 @default.
- W2105160541 hasConceptScore W2105160541C28490314 @default.
- W2105160541 hasConceptScore W2105160541C31258907 @default.
- W2105160541 hasConceptScore W2105160541C33923547 @default.
- W2105160541 hasConceptScore W2105160541C41008148 @default.
- W2105160541 hasConceptScore W2105160541C50644808 @default.
- W2105160541 hasConceptScore W2105160541C61224824 @default.
- W2105160541 hasIssue "5" @default.
- W2105160541 hasLocation W21051605411 @default.
- W2105160541 hasOpenAccess W2105160541 @default.
- W2105160541 hasPrimaryLocation W21051605411 @default.
- W2105160541 hasRelatedWork W1505497582 @default.
- W2105160541 hasRelatedWork W1528914981 @default.
- W2105160541 hasRelatedWork W1562793155 @default.
- W2105160541 hasRelatedWork W1598110435 @default.
- W2105160541 hasRelatedWork W1975561281 @default.
- W2105160541 hasRelatedWork W2076520961 @default.
- W2105160541 hasRelatedWork W2548184953 @default.
- W2105160541 hasRelatedWork W2742991909 @default.
- W2105160541 hasRelatedWork W2767651786 @default.