Matches in SemOpenAlex for { <https://semopenalex.org/work/W2021103260> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W2021103260 abstract "Neural and stochastic models for signal classification generate output probabilities to indicate whether or not their inputs are members of the modeled class. This paper presents a feature enhancing neural network with weights based on the modeled class which can improve the classification performance of single output classifiers, by increasing output probabilities for members of the modeled class or decreasing output probabilities for non-members. The neural network is demonstrated as a front-end for multi-layer perceptron and semi-continuous hidden Markov model based classifiers for speech recognition applications. It is unique in that the weights and width of the input layer adapt based on extracted characteristics from the input speech signal. The connectionist architecture is motivated by the highly successful time-delay neural network and the desire to find efficient training procedures for class-dependent, short- time transformations. The weights are determined using a principal component analysis process and can be found by applying iterative or conventional algorithms. The neural network reduces false acceptances by more than one-third for a defined mono-syllable keyword spotting application using a semi-continuous hidden Markov model based system. An evaluation of the neural network as a front-end for multi-layer perceptron based classifiers which distinguish a word from confusable words is also presented.© (1992) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only." @default.
- W2021103260 created "2016-06-24" @default.
- W2021103260 creator A5057910370 @default.
- W2021103260 creator A5080911954 @default.
- W2021103260 date "1992-12-16" @default.
- W2021103260 modified "2023-09-27" @default.
- W2021103260 title "<title>Feature enhancement for multilayer perceptron and semicontinuous hidden Markov model-based classifiers using neural networks</title>" @default.
- W2021103260 doi "https://doi.org/10.1117/12.130858" @default.
- W2021103260 hasPublicationYear "1992" @default.
- W2021103260 type Work @default.
- W2021103260 sameAs 2021103260 @default.
- W2021103260 citedByCount "2" @default.
- W2021103260 crossrefType "proceedings-article" @default.
- W2021103260 hasAuthorship W2021103260A5057910370 @default.
- W2021103260 hasAuthorship W2021103260A5080911954 @default.
- W2021103260 hasConcept C119857082 @default.
- W2021103260 hasConcept C138885662 @default.
- W2021103260 hasConcept C153180895 @default.
- W2021103260 hasConcept C154945302 @default.
- W2021103260 hasConcept C175202392 @default.
- W2021103260 hasConcept C179717631 @default.
- W2021103260 hasConcept C23224414 @default.
- W2021103260 hasConcept C2776401178 @default.
- W2021103260 hasConcept C28490314 @default.
- W2021103260 hasConcept C41008148 @default.
- W2021103260 hasConcept C41895202 @default.
- W2021103260 hasConcept C50644808 @default.
- W2021103260 hasConcept C60908668 @default.
- W2021103260 hasConcept C8521452 @default.
- W2021103260 hasConceptScore W2021103260C119857082 @default.
- W2021103260 hasConceptScore W2021103260C138885662 @default.
- W2021103260 hasConceptScore W2021103260C153180895 @default.
- W2021103260 hasConceptScore W2021103260C154945302 @default.
- W2021103260 hasConceptScore W2021103260C175202392 @default.
- W2021103260 hasConceptScore W2021103260C179717631 @default.
- W2021103260 hasConceptScore W2021103260C23224414 @default.
- W2021103260 hasConceptScore W2021103260C2776401178 @default.
- W2021103260 hasConceptScore W2021103260C28490314 @default.
- W2021103260 hasConceptScore W2021103260C41008148 @default.
- W2021103260 hasConceptScore W2021103260C41895202 @default.
- W2021103260 hasConceptScore W2021103260C50644808 @default.
- W2021103260 hasConceptScore W2021103260C60908668 @default.
- W2021103260 hasConceptScore W2021103260C8521452 @default.
- W2021103260 hasLocation W20211032601 @default.
- W2021103260 hasOpenAccess W2021103260 @default.
- W2021103260 hasPrimaryLocation W20211032601 @default.
- W2021103260 hasRelatedWork W1570584848 @default.
- W2021103260 hasRelatedWork W2060174408 @default.
- W2021103260 hasRelatedWork W2142708963 @default.
- W2021103260 hasRelatedWork W2259070405 @default.
- W2021103260 hasRelatedWork W2482291232 @default.
- W2021103260 hasRelatedWork W2793348512 @default.
- W2021103260 hasRelatedWork W2943073572 @default.
- W2021103260 hasRelatedWork W3011654750 @default.
- W2021103260 hasRelatedWork W3016747886 @default.
- W2021103260 hasRelatedWork W3036053385 @default.
- W2021103260 hasRelatedWork W3048819688 @default.
- W2021103260 hasRelatedWork W3118973577 @default.
- W2021103260 hasRelatedWork W3151076433 @default.
- W2021103260 hasRelatedWork W3152185262 @default.
- W2021103260 hasRelatedWork W3153277386 @default.
- W2021103260 hasRelatedWork W3193358615 @default.
- W2021103260 hasRelatedWork W408314575 @default.
- W2021103260 hasRelatedWork W46039496 @default.
- W2021103260 hasRelatedWork W2840113469 @default.
- W2021103260 hasRelatedWork W2926324512 @default.
- W2021103260 isParatext "false" @default.
- W2021103260 isRetracted "false" @default.
- W2021103260 magId "2021103260" @default.
- W2021103260 workType "article" @default.