Matches in SemOpenAlex for { <https://semopenalex.org/work/W2093028810> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W2093028810 abstract "Recently there has been interest in combining generative and discriminative classifiers. In these classifiers features for the discriminative models are derived from the generative kernels. One advantage of using generative kernels is that systematic approaches exist to introduce complex dependencies into the feature-space. Furthermore, as the features are based on generative models standard model-based compensation and adaptation techniques can be applied to make discriminative models robust to noise and speaker conditions. This paper extends previous work in this framework in several directions. First, it introduces derivative kernels based on context-dependent generative models. Second, it describes how derivative kernels can be incorporated in structured discriminative models. Third, it addresses the issues associated with large number of classes and parameters when context-dependent models and high-dimensional feature-spaces of derivative kernels are used. The approach is evaluated on two noise-corrupted tasks: small vocabulary AURORA 2 and medium-to-large vocabulary AURORA 4 task." @default.
- W2093028810 created "2016-06-24" @default.
- W2093028810 creator A5012703069 @default.
- W2093028810 creator A5024283093 @default.
- W2093028810 date "2011-12-01" @default.
- W2093028810 modified "2023-09-25" @default.
- W2093028810 title "Derivative kernels for noise robust ASR" @default.
- W2093028810 cites W1487784522 @default.
- W2093028810 cites W1599512239 @default.
- W2093028810 cites W2111539083 @default.
- W2093028810 cites W2115281877 @default.
- W2093028810 cites W2131033001 @default.
- W2093028810 cites W2146423524 @default.
- W2093028810 cites W2154198224 @default.
- W2093028810 cites W2158069733 @default.
- W2093028810 cites W2169272853 @default.
- W2093028810 cites W853436745 @default.
- W2093028810 doi "https://doi.org/10.1109/asru.2011.6163916" @default.
- W2093028810 hasPublicationYear "2011" @default.
- W2093028810 type Work @default.
- W2093028810 sameAs 2093028810 @default.
- W2093028810 citedByCount "21" @default.
- W2093028810 countsByYear W20930288102012 @default.
- W2093028810 countsByYear W20930288102013 @default.
- W2093028810 countsByYear W20930288102014 @default.
- W2093028810 countsByYear W20930288102015 @default.
- W2093028810 countsByYear W20930288102016 @default.
- W2093028810 countsByYear W20930288102019 @default.
- W2093028810 countsByYear W20930288102020 @default.
- W2093028810 crossrefType "proceedings-article" @default.
- W2093028810 hasAuthorship W2093028810A5012703069 @default.
- W2093028810 hasAuthorship W2093028810A5024283093 @default.
- W2093028810 hasBestOaLocation W20930288102 @default.
- W2093028810 hasConcept C106159729 @default.
- W2093028810 hasConcept C111771559 @default.
- W2093028810 hasConcept C115961682 @default.
- W2093028810 hasConcept C154945302 @default.
- W2093028810 hasConcept C162324750 @default.
- W2093028810 hasConcept C163294075 @default.
- W2093028810 hasConcept C28490314 @default.
- W2093028810 hasConcept C29265498 @default.
- W2093028810 hasConcept C41008148 @default.
- W2093028810 hasConcept C99498987 @default.
- W2093028810 hasConceptScore W2093028810C106159729 @default.
- W2093028810 hasConceptScore W2093028810C111771559 @default.
- W2093028810 hasConceptScore W2093028810C115961682 @default.
- W2093028810 hasConceptScore W2093028810C154945302 @default.
- W2093028810 hasConceptScore W2093028810C162324750 @default.
- W2093028810 hasConceptScore W2093028810C163294075 @default.
- W2093028810 hasConceptScore W2093028810C28490314 @default.
- W2093028810 hasConceptScore W2093028810C29265498 @default.
- W2093028810 hasConceptScore W2093028810C41008148 @default.
- W2093028810 hasConceptScore W2093028810C99498987 @default.
- W2093028810 hasLocation W20930288101 @default.
- W2093028810 hasLocation W20930288102 @default.
- W2093028810 hasOpenAccess W2093028810 @default.
- W2093028810 hasPrimaryLocation W20930288101 @default.
- W2093028810 hasRelatedWork W1705301983 @default.
- W2093028810 hasRelatedWork W2020163257 @default.
- W2093028810 hasRelatedWork W2040365831 @default.
- W2093028810 hasRelatedWork W2076268407 @default.
- W2093028810 hasRelatedWork W2078083007 @default.
- W2093028810 hasRelatedWork W2117857642 @default.
- W2093028810 hasRelatedWork W2355125052 @default.
- W2093028810 hasRelatedWork W2397741330 @default.
- W2093028810 hasRelatedWork W2405206884 @default.
- W2093028810 hasRelatedWork W2407094086 @default.
- W2093028810 isParatext "false" @default.
- W2093028810 isRetracted "false" @default.
- W2093028810 magId "2093028810" @default.
- W2093028810 workType "article" @default.