Matches in SemOpenAlex for { <https://semopenalex.org/work/W2022202116> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2022202116 endingPage "843" @default.
- W2022202116 startingPage "836" @default.
- W2022202116 abstract "The impact on speech recognition performance in a distributed speech recognition (DSR) environment of two methods used to reduce the dimension of the feature vectors is examined in this paper. The motivation behind reducing the dimension of the feature set is to reduce the bandwidth required to send the feature vectors over a channel from the client front-end to the server back-end in a DSR system. In the first approach, the features are empirically chosen to maximise recognition performance. A data-centric transform-based dimensionality-reduction technique is applied in the second case. Test results for the empirical approach show that individual coefficients have different impacts on the speech recognition performance, and that certain coefficients should always be present in an empirically selected reduced feature set for given training and test conditions. Initial results show that for the empirical method, the number of elements in a feature vector produced by an established DSR front-end can be reduced by 23% with low impact on the recognition performance (less than 8% relative performance drop compared to the full bandwidth case). Using the transform-based approach, for a similar impact on recognition performance, the number of feature vector elements can be reduced by 30%. Furthermore, for best recognition performance, the results indicate that the SNR of the speech signal should be considered using either approach when selecting the feature vector elements that are to be included in a reduced feature set." @default.
- W2022202116 created "2016-06-24" @default.
- W2022202116 creator A5008448972 @default.
- W2022202116 creator A5014986870 @default.
- W2022202116 date "2012-07-01" @default.
- W2022202116 modified "2023-10-01" @default.
- W2022202116 title "Feature selection for reduced-bandwidth distributed speech recognition" @default.
- W2022202116 cites W125001557 @default.
- W2022202116 cites W1502016700 @default.
- W2022202116 cites W1877910628 @default.
- W2022202116 cites W1981663210 @default.
- W2022202116 cites W2013115497 @default.
- W2022202116 cites W2037552098 @default.
- W2022202116 cites W2080400971 @default.
- W2022202116 cites W2106554350 @default.
- W2022202116 cites W2109371829 @default.
- W2022202116 cites W2111600990 @default.
- W2022202116 cites W2113107931 @default.
- W2022202116 cites W2120184544 @default.
- W2022202116 cites W2148154194 @default.
- W2022202116 cites W2151484683 @default.
- W2022202116 cites W2247516327 @default.
- W2022202116 cites W3031363333 @default.
- W2022202116 doi "https://doi.org/10.1016/j.specom.2012.01.003" @default.
- W2022202116 hasPublicationYear "2012" @default.
- W2022202116 type Work @default.
- W2022202116 sameAs 2022202116 @default.
- W2022202116 citedByCount "4" @default.
- W2022202116 countsByYear W20222021162013 @default.
- W2022202116 countsByYear W20222021162014 @default.
- W2022202116 countsByYear W20222021162015 @default.
- W2022202116 countsByYear W20222021162016 @default.
- W2022202116 crossrefType "journal-article" @default.
- W2022202116 hasAuthorship W2022202116A5008448972 @default.
- W2022202116 hasAuthorship W2022202116A5014986870 @default.
- W2022202116 hasConcept C138885662 @default.
- W2022202116 hasConcept C148483581 @default.
- W2022202116 hasConcept C153180895 @default.
- W2022202116 hasConcept C154945302 @default.
- W2022202116 hasConcept C2776257435 @default.
- W2022202116 hasConcept C2776401178 @default.
- W2022202116 hasConcept C28490314 @default.
- W2022202116 hasConcept C31258907 @default.
- W2022202116 hasConcept C41008148 @default.
- W2022202116 hasConcept C41895202 @default.
- W2022202116 hasConcept C61328038 @default.
- W2022202116 hasConcept C81917197 @default.
- W2022202116 hasConceptScore W2022202116C138885662 @default.
- W2022202116 hasConceptScore W2022202116C148483581 @default.
- W2022202116 hasConceptScore W2022202116C153180895 @default.
- W2022202116 hasConceptScore W2022202116C154945302 @default.
- W2022202116 hasConceptScore W2022202116C2776257435 @default.
- W2022202116 hasConceptScore W2022202116C2776401178 @default.
- W2022202116 hasConceptScore W2022202116C28490314 @default.
- W2022202116 hasConceptScore W2022202116C31258907 @default.
- W2022202116 hasConceptScore W2022202116C41008148 @default.
- W2022202116 hasConceptScore W2022202116C41895202 @default.
- W2022202116 hasConceptScore W2022202116C61328038 @default.
- W2022202116 hasConceptScore W2022202116C81917197 @default.
- W2022202116 hasIssue "6" @default.
- W2022202116 hasLocation W20222021161 @default.
- W2022202116 hasOpenAccess W2022202116 @default.
- W2022202116 hasPrimaryLocation W20222021161 @default.
- W2022202116 hasRelatedWork W2013349038 @default.
- W2022202116 hasRelatedWork W2159220931 @default.
- W2022202116 hasRelatedWork W2316780152 @default.
- W2022202116 hasRelatedWork W2374344280 @default.
- W2022202116 hasRelatedWork W2547204049 @default.
- W2022202116 hasRelatedWork W27971500 @default.
- W2022202116 hasRelatedWork W2891907751 @default.
- W2022202116 hasRelatedWork W2970216048 @default.
- W2022202116 hasRelatedWork W4307883119 @default.
- W2022202116 hasRelatedWork W2345184372 @default.
- W2022202116 hasVolume "54" @default.
- W2022202116 isParatext "false" @default.
- W2022202116 isRetracted "false" @default.
- W2022202116 magId "2022202116" @default.
- W2022202116 workType "article" @default.