Matches in SemOpenAlex for { <https://semopenalex.org/work/W1999625574> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W1999625574 endingPage "2113" @default.
- W1999625574 startingPage "2105" @default.
- W1999625574 abstract "A smoothing method for minimum phone error linear regression (MPELR) is proposed in this paper. We show that the objective function for minimum phone error (MPE) can be combined with a prior mean distribution. When the prior mean distribution is based on maximum likelihood (ML) estimates, the proposed method is the same as the previous smoothing technique for MPELR. Instead of ML estimates, maximum a posteriori (MAP) parameter estimate is used to define the mode of prior mean distribution to improve the performance of MPELR. Experiments on a large vocabulary speech recognition task show that the proposed method can obtain 8.4% relative reduction in word error rate when the amount of data is limited, while retaining the same asymptotic performance as conventional MPELR. When compared with discriminative maximum a posteriori linear regression (DMAPLR), the proposed method shows improvement except for the case of limited adaptation data for supervised adaptation." @default.
- W1999625574 created "2016-06-24" @default.
- W1999625574 creator A5018911822 @default.
- W1999625574 creator A5031150833 @default.
- W1999625574 creator A5037184751 @default.
- W1999625574 creator A5066595006 @default.
- W1999625574 creator A5089901619 @default.
- W1999625574 date "2014-01-01" @default.
- W1999625574 modified "2023-10-04" @default.
- W1999625574 title "Smoothing Method for Improved Minimum Phone Error Linear Regression" @default.
- W1999625574 cites W117579468 @default.
- W1999625574 cites W184549729 @default.
- W1999625574 cites W2002342963 @default.
- W1999625574 cites W2003123121 @default.
- W1999625574 cites W2037740282 @default.
- W1999625574 cites W2058216438 @default.
- W1999625574 cites W2066561607 @default.
- W1999625574 cites W2080400971 @default.
- W1999625574 cites W2081976287 @default.
- W1999625574 cites W2100969003 @default.
- W1999625574 cites W2141054030 @default.
- W1999625574 cites W2146871184 @default.
- W1999625574 cites W2157159979 @default.
- W1999625574 cites W2158069733 @default.
- W1999625574 cites W2327169953 @default.
- W1999625574 doi "https://doi.org/10.1587/transinf.e97.d.2105" @default.
- W1999625574 hasPublicationYear "2014" @default.
- W1999625574 type Work @default.
- W1999625574 sameAs 1999625574 @default.
- W1999625574 citedByCount "0" @default.
- W1999625574 crossrefType "journal-article" @default.
- W1999625574 hasAuthorship W1999625574A5018911822 @default.
- W1999625574 hasAuthorship W1999625574A5031150833 @default.
- W1999625574 hasAuthorship W1999625574A5037184751 @default.
- W1999625574 hasAuthorship W1999625574A5066595006 @default.
- W1999625574 hasAuthorship W1999625574A5089901619 @default.
- W1999625574 hasBestOaLocation W19996255741 @default.
- W1999625574 hasConcept C105795698 @default.
- W1999625574 hasConcept C111472728 @default.
- W1999625574 hasConcept C11413529 @default.
- W1999625574 hasConcept C119857082 @default.
- W1999625574 hasConcept C138885662 @default.
- W1999625574 hasConcept C139945424 @default.
- W1999625574 hasConcept C153180895 @default.
- W1999625574 hasConcept C154945302 @default.
- W1999625574 hasConcept C185429906 @default.
- W1999625574 hasConcept C28490314 @default.
- W1999625574 hasConcept C31972630 @default.
- W1999625574 hasConcept C33923547 @default.
- W1999625574 hasConcept C3770464 @default.
- W1999625574 hasConcept C40969351 @default.
- W1999625574 hasConcept C41008148 @default.
- W1999625574 hasConcept C48921125 @default.
- W1999625574 hasConcept C49781872 @default.
- W1999625574 hasConcept C75553542 @default.
- W1999625574 hasConcept C90652560 @default.
- W1999625574 hasConcept C97931131 @default.
- W1999625574 hasConcept C9810830 @default.
- W1999625574 hasConceptScore W1999625574C105795698 @default.
- W1999625574 hasConceptScore W1999625574C111472728 @default.
- W1999625574 hasConceptScore W1999625574C11413529 @default.
- W1999625574 hasConceptScore W1999625574C119857082 @default.
- W1999625574 hasConceptScore W1999625574C138885662 @default.
- W1999625574 hasConceptScore W1999625574C139945424 @default.
- W1999625574 hasConceptScore W1999625574C153180895 @default.
- W1999625574 hasConceptScore W1999625574C154945302 @default.
- W1999625574 hasConceptScore W1999625574C185429906 @default.
- W1999625574 hasConceptScore W1999625574C28490314 @default.
- W1999625574 hasConceptScore W1999625574C31972630 @default.
- W1999625574 hasConceptScore W1999625574C33923547 @default.
- W1999625574 hasConceptScore W1999625574C3770464 @default.
- W1999625574 hasConceptScore W1999625574C40969351 @default.
- W1999625574 hasConceptScore W1999625574C41008148 @default.
- W1999625574 hasConceptScore W1999625574C48921125 @default.
- W1999625574 hasConceptScore W1999625574C49781872 @default.
- W1999625574 hasConceptScore W1999625574C75553542 @default.
- W1999625574 hasConceptScore W1999625574C90652560 @default.
- W1999625574 hasConceptScore W1999625574C97931131 @default.
- W1999625574 hasConceptScore W1999625574C9810830 @default.
- W1999625574 hasIssue "8" @default.
- W1999625574 hasLocation W19996255741 @default.
- W1999625574 hasOpenAccess W1999625574 @default.
- W1999625574 hasPrimaryLocation W19996255741 @default.
- W1999625574 hasRelatedWork W1652783584 @default.
- W1999625574 hasRelatedWork W1990254706 @default.
- W1999625574 hasRelatedWork W2005467145 @default.
- W1999625574 hasRelatedWork W2024160000 @default.
- W1999625574 hasRelatedWork W2061273563 @default.
- W1999625574 hasRelatedWork W2166265134 @default.
- W1999625574 hasRelatedWork W2285052147 @default.
- W1999625574 hasRelatedWork W2729514902 @default.
- W1999625574 hasRelatedWork W2773500201 @default.
- W1999625574 hasRelatedWork W8493306 @default.
- W1999625574 hasVolume "E97.D" @default.
- W1999625574 isParatext "false" @default.
- W1999625574 isRetracted "false" @default.
- W1999625574 magId "1999625574" @default.
- W1999625574 workType "article" @default.