Matches in SemOpenAlex for { <https://semopenalex.org/work/W2162912381> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2162912381 endingPage "211" @default.
- W2162912381 startingPage "205" @default.
- W2162912381 abstract "• We propose a regression-based method for estimating the speech absence uncertainty. • The regression model was trained under the various noise and SNR conditions. • The proposed method showed better performance than other algorithms. We propose a novel approach to improve the performance of speech enhancement systems by using multiple linear regression to improve the technique of estimating the speech presence uncertainty. Conventional speech enhancement techniques use a fixed ratio Q of the a priori probability of speech presence and speech absence, or determine the value of Q simply by comparing one particular parameter against a threshold in deriving the speech absence probability (SAP) associated with the speech presence uncertainty. To further improve the performance of the SAP, we attempt to adaptively change Q according to a linear model consisting of the regression coefficients obtained by results from multiple linear regression analysis and two principal parameters: a priori SNR and the ratio between the local energy of the noisy speech and its derived minimum since these parameters correlate strongly with the value of Q . Distinct values of Q for each frequency in each frame are consequently assigned in time which leads to improved tracking performance of speech absence uncertainty and thus better performance of the proposed speech enhancement compared to conventional approaches. The superiority of the proposed approach is confirmed through extensive objective and subjective evaluations under various noise conditions." @default.
- W2162912381 created "2016-06-24" @default.
- W2162912381 creator A5002418613 @default.
- W2162912381 creator A5004712180 @default.
- W2162912381 creator A5041914914 @default.
- W2162912381 creator A5051356511 @default.
- W2162912381 creator A5069071162 @default.
- W2162912381 date "2015-01-01" @default.
- W2162912381 modified "2023-09-24" @default.
- W2162912381 title "Estimation of speech absence uncertainty based on multiple linear regression analysis for speech enhancement" @default.
- W2162912381 cites W1974387177 @default.
- W2162912381 cites W1975301756 @default.
- W2162912381 cites W2027933188 @default.
- W2162912381 cites W2034562813 @default.
- W2162912381 cites W2042202802 @default.
- W2162912381 cites W2078528584 @default.
- W2162912381 cites W2108819501 @default.
- W2162912381 cites W2111211434 @default.
- W2162912381 cites W2121894251 @default.
- W2162912381 cites W2121973264 @default.
- W2162912381 cites W2144404214 @default.
- W2162912381 cites W2153894152 @default.
- W2162912381 cites W2157242178 @default.
- W2162912381 cites W2163839957 @default.
- W2162912381 cites W2165895664 @default.
- W2162912381 cites W2169147844 @default.
- W2162912381 cites W2172246201 @default.
- W2162912381 cites W3127686677 @default.
- W2162912381 cites W3147539069 @default.
- W2162912381 doi "https://doi.org/10.1016/j.apacoust.2014.06.017" @default.
- W2162912381 hasPublicationYear "2015" @default.
- W2162912381 type Work @default.
- W2162912381 sameAs 2162912381 @default.
- W2162912381 citedByCount "5" @default.
- W2162912381 countsByYear W21629123812015 @default.
- W2162912381 countsByYear W21629123812016 @default.
- W2162912381 countsByYear W21629123812018 @default.
- W2162912381 countsByYear W21629123812022 @default.
- W2162912381 crossrefType "journal-article" @default.
- W2162912381 hasAuthorship W2162912381A5002418613 @default.
- W2162912381 hasAuthorship W2162912381A5004712180 @default.
- W2162912381 hasAuthorship W2162912381A5041914914 @default.
- W2162912381 hasAuthorship W2162912381A5051356511 @default.
- W2162912381 hasAuthorship W2162912381A5069071162 @default.
- W2162912381 hasConcept C105795698 @default.
- W2162912381 hasConcept C111472728 @default.
- W2162912381 hasConcept C115961682 @default.
- W2162912381 hasConcept C131109320 @default.
- W2162912381 hasConcept C138885662 @default.
- W2162912381 hasConcept C152877465 @default.
- W2162912381 hasConcept C154945302 @default.
- W2162912381 hasConcept C163294075 @default.
- W2162912381 hasConcept C2776182073 @default.
- W2162912381 hasConcept C28490314 @default.
- W2162912381 hasConcept C33923547 @default.
- W2162912381 hasConcept C41008148 @default.
- W2162912381 hasConcept C48921125 @default.
- W2162912381 hasConcept C59883199 @default.
- W2162912381 hasConcept C61328038 @default.
- W2162912381 hasConcept C75553542 @default.
- W2162912381 hasConcept C83546350 @default.
- W2162912381 hasConcept C99498987 @default.
- W2162912381 hasConceptScore W2162912381C105795698 @default.
- W2162912381 hasConceptScore W2162912381C111472728 @default.
- W2162912381 hasConceptScore W2162912381C115961682 @default.
- W2162912381 hasConceptScore W2162912381C131109320 @default.
- W2162912381 hasConceptScore W2162912381C138885662 @default.
- W2162912381 hasConceptScore W2162912381C152877465 @default.
- W2162912381 hasConceptScore W2162912381C154945302 @default.
- W2162912381 hasConceptScore W2162912381C163294075 @default.
- W2162912381 hasConceptScore W2162912381C2776182073 @default.
- W2162912381 hasConceptScore W2162912381C28490314 @default.
- W2162912381 hasConceptScore W2162912381C33923547 @default.
- W2162912381 hasConceptScore W2162912381C41008148 @default.
- W2162912381 hasConceptScore W2162912381C48921125 @default.
- W2162912381 hasConceptScore W2162912381C59883199 @default.
- W2162912381 hasConceptScore W2162912381C61328038 @default.
- W2162912381 hasConceptScore W2162912381C75553542 @default.
- W2162912381 hasConceptScore W2162912381C83546350 @default.
- W2162912381 hasConceptScore W2162912381C99498987 @default.
- W2162912381 hasLocation W21629123811 @default.
- W2162912381 hasOpenAccess W2162912381 @default.
- W2162912381 hasPrimaryLocation W21629123811 @default.
- W2162912381 hasRelatedWork W1573346329 @default.
- W2162912381 hasRelatedWork W1999835922 @default.
- W2162912381 hasRelatedWork W2121858826 @default.
- W2162912381 hasRelatedWork W2122760606 @default.
- W2162912381 hasRelatedWork W2139819017 @default.
- W2162912381 hasRelatedWork W2152180908 @default.
- W2162912381 hasRelatedWork W2155010696 @default.
- W2162912381 hasRelatedWork W2162912381 @default.
- W2162912381 hasRelatedWork W2289873871 @default.
- W2162912381 hasRelatedWork W3211091508 @default.
- W2162912381 hasVolume "87" @default.
- W2162912381 isParatext "false" @default.
- W2162912381 isRetracted "false" @default.
- W2162912381 magId "2162912381" @default.
- W2162912381 workType "article" @default.