Matches in SemOpenAlex for { <https://semopenalex.org/work/W94928940> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W94928940 abstract "In statistical speech recognition, misclassification often occurs when there is a mismatch between the incoming signal and the acoustics model inside the recognizer. In order to combat this problem, techniques such as Cepstral Mean Subtraction, Vocal Tract Normalization, adaptation and pronunciation model can be used. In this paper, we proposed a new approach based on transformation technique where the output distribution function in the HMM model, a Gaussian probability density function, could be transformed to match the estimated distribution of the incoming signal by using a memoryless invertible nonlinearity function. Since the new density still has a Gaussian form, the function could be completely characterized by using the Expectation Maximization (EM) algorithm." @default.
- W94928940 created "2016-06-24" @default.
- W94928940 creator A5007781589 @default.
- W94928940 creator A5010546001 @default.
- W94928940 creator A5026951061 @default.
- W94928940 creator A5074775505 @default.
- W94928940 creator A5088558589 @default.
- W94928940 date "2000-10-16" @default.
- W94928940 modified "2023-09-27" @default.
- W94928940 title "Improved acoustics modeling for speech recognition using transformation techniques" @default.
- W94928940 cites W1560013842 @default.
- W94928940 cites W2014089984 @default.
- W94928940 cites W2065371079 @default.
- W94928940 cites W2158577652 @default.
- W94928940 cites W3148186152 @default.
- W94928940 cites W2797816625 @default.
- W94928940 doi "https://doi.org/10.21437/icslp.2000-780" @default.
- W94928940 hasPublicationYear "2000" @default.
- W94928940 type Work @default.
- W94928940 sameAs 94928940 @default.
- W94928940 citedByCount "0" @default.
- W94928940 crossrefType "proceedings-article" @default.
- W94928940 hasAuthorship W94928940A5007781589 @default.
- W94928940 hasAuthorship W94928940A5010546001 @default.
- W94928940 hasAuthorship W94928940A5026951061 @default.
- W94928940 hasAuthorship W94928940A5074775505 @default.
- W94928940 hasAuthorship W94928940A5088558589 @default.
- W94928940 hasConcept C104317684 @default.
- W94928940 hasConcept C121332964 @default.
- W94928940 hasConcept C155635449 @default.
- W94928940 hasConcept C185592680 @default.
- W94928940 hasConcept C204241405 @default.
- W94928940 hasConcept C24890656 @default.
- W94928940 hasConcept C28490314 @default.
- W94928940 hasConcept C41008148 @default.
- W94928940 hasConcept C55493867 @default.
- W94928940 hasConcept C61328038 @default.
- W94928940 hasConceptScore W94928940C104317684 @default.
- W94928940 hasConceptScore W94928940C121332964 @default.
- W94928940 hasConceptScore W94928940C155635449 @default.
- W94928940 hasConceptScore W94928940C185592680 @default.
- W94928940 hasConceptScore W94928940C204241405 @default.
- W94928940 hasConceptScore W94928940C24890656 @default.
- W94928940 hasConceptScore W94928940C28490314 @default.
- W94928940 hasConceptScore W94928940C41008148 @default.
- W94928940 hasConceptScore W94928940C55493867 @default.
- W94928940 hasConceptScore W94928940C61328038 @default.
- W94928940 hasLocation W949289401 @default.
- W94928940 hasOpenAccess W94928940 @default.
- W94928940 hasPrimaryLocation W949289401 @default.
- W94928940 hasRelatedWork W2157598242 @default.
- W94928940 hasRelatedWork W2368779261 @default.
- W94928940 hasRelatedWork W2374918184 @default.
- W94928940 hasRelatedWork W2414841434 @default.
- W94928940 hasRelatedWork W2793122029 @default.
- W94928940 hasRelatedWork W3143423642 @default.
- W94928940 hasRelatedWork W3144782693 @default.
- W94928940 hasRelatedWork W3151376046 @default.
- W94928940 hasRelatedWork W642007152 @default.
- W94928940 hasRelatedWork W2992378684 @default.
- W94928940 isParatext "false" @default.
- W94928940 isRetracted "false" @default.
- W94928940 magId "94928940" @default.
- W94928940 workType "article" @default.