Matches in SemOpenAlex for { <https://semopenalex.org/work/W1567768635> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W1567768635 abstract "A new training algorithm called the approximated maximum mutual information (AMMI) is proposed to improve the accuracy of myoelectric speech recognition using hidden Markov models (HMMs). Previous studies have demonstrated that automatic speech recognition can be performed using myoelectric signals from articulatory muscles of the face. Classification of facial myoelectric signals can be performed using HMMs that are trained using the maximum likelihood (ML) algorithm; however, this algorithm maximizes the likelihood of the observations in the training sequence, which is not directly associated with optimal classification accuracy. The AMMI training algorithm attempts to maximize the mutual information, thereby training the HMMs to optimize their parameters for discrimination. Our results show that AMMI training consistently reduces the error rates compared to these by the ML training, increasing the accuracy by approximately 3% on average." @default.
- W1567768635 created "2016-06-24" @default.
- W1567768635 creator A5047839047 @default.
- W1567768635 creator A5057240627 @default.
- W1567768635 date "2006-08-01" @default.
- W1567768635 modified "2023-09-23" @default.
- W1567768635 title "Approximated Mutual Information Training for Speech Recognition Using Myoelectric Signals" @default.
- W1567768635 cites W1877570817 @default.
- W1567768635 cites W190227032 @default.
- W1567768635 cites W2012745928 @default.
- W1567768635 cites W2045503624 @default.
- W1567768635 cites W2048173531 @default.
- W1567768635 cites W2095661886 @default.
- W1567768635 cites W2100969003 @default.
- W1567768635 cites W2109299006 @default.
- W1567768635 cites W2125838338 @default.
- W1567768635 cites W2129072127 @default.
- W1567768635 cites W2149250980 @default.
- W1567768635 doi "https://doi.org/10.1109/iembs.2006.259992" @default.
- W1567768635 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/17945600" @default.
- W1567768635 hasPublicationYear "2006" @default.
- W1567768635 type Work @default.
- W1567768635 sameAs 1567768635 @default.
- W1567768635 citedByCount "0" @default.
- W1567768635 crossrefType "proceedings-article" @default.
- W1567768635 hasAuthorship W1567768635A5047839047 @default.
- W1567768635 hasAuthorship W1567768635A5057240627 @default.
- W1567768635 hasConcept C105795698 @default.
- W1567768635 hasConcept C152139883 @default.
- W1567768635 hasConcept C153180895 @default.
- W1567768635 hasConcept C154945302 @default.
- W1567768635 hasConcept C23224414 @default.
- W1567768635 hasConcept C28490314 @default.
- W1567768635 hasConcept C33923547 @default.
- W1567768635 hasConcept C41008148 @default.
- W1567768635 hasConcept C49781872 @default.
- W1567768635 hasConceptScore W1567768635C105795698 @default.
- W1567768635 hasConceptScore W1567768635C152139883 @default.
- W1567768635 hasConceptScore W1567768635C153180895 @default.
- W1567768635 hasConceptScore W1567768635C154945302 @default.
- W1567768635 hasConceptScore W1567768635C23224414 @default.
- W1567768635 hasConceptScore W1567768635C28490314 @default.
- W1567768635 hasConceptScore W1567768635C33923547 @default.
- W1567768635 hasConceptScore W1567768635C41008148 @default.
- W1567768635 hasConceptScore W1567768635C49781872 @default.
- W1567768635 hasLocation W15677686351 @default.
- W1567768635 hasLocation W15677686352 @default.
- W1567768635 hasOpenAccess W1567768635 @default.
- W1567768635 hasPrimaryLocation W15677686351 @default.
- W1567768635 hasRelatedWork W1481751294 @default.
- W1567768635 hasRelatedWork W1548481688 @default.
- W1567768635 hasRelatedWork W1567768635 @default.
- W1567768635 hasRelatedWork W2011502238 @default.
- W1567768635 hasRelatedWork W2023185280 @default.
- W1567768635 hasRelatedWork W2160799648 @default.
- W1567768635 hasRelatedWork W2539985974 @default.
- W1567768635 hasRelatedWork W2793122029 @default.
- W1567768635 hasRelatedWork W2963474932 @default.
- W1567768635 hasRelatedWork W59017505 @default.
- W1567768635 isParatext "false" @default.
- W1567768635 isRetracted "false" @default.
- W1567768635 magId "1567768635" @default.
- W1567768635 workType "article" @default.