Matches in SemOpenAlex for { <https://semopenalex.org/work/W2106051978> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2106051978 abstract "Deep Belief Networks (DBNs) are multi-layer generative models. They can be trained to model windows of coefficients extracted from speech and they discover multiple layers of features that capture the higher-order statistical structure of the data. These features can be used to initialize the hidden units of a feed-forward neural network that is then trained to predict the HMM state for the central frame of the window. Initializing with features that are good at generating speech makes the neural network perform much better than initializing with random weights. DBNs have already been used successfully for phone recognition with input coefficients that are MFCCs or filterbank outputs. In this paper, we demonstrate that they work even better when their inputs are speaker adaptive, discriminative features. On the standard TIMIT corpus, they give phone error rates of 19.6% using monophone HMMs and a bigram language model and 19.4% using monophone HMMs and a trigram language model." @default.
- W2106051978 created "2016-06-24" @default.
- W2106051978 creator A5024209719 @default.
- W2106051978 creator A5034529775 @default.
- W2106051978 creator A5042186348 @default.
- W2106051978 creator A5047062711 @default.
- W2106051978 creator A5070513394 @default.
- W2106051978 creator A5071715737 @default.
- W2106051978 date "2011-05-01" @default.
- W2106051978 modified "2023-10-18" @default.
- W2106051978 title "Deep Belief Networks using discriminative features for phone recognition" @default.
- W2106051978 cites W1994197834 @default.
- W2106051978 cites W2002342963 @default.
- W2106051978 cites W2077804127 @default.
- W2106051978 cites W2116064496 @default.
- W2106051978 cites W2136922672 @default.
- W2106051978 cites W2155117693 @default.
- W2106051978 cites W2158289097 @default.
- W2106051978 doi "https://doi.org/10.1109/icassp.2011.5947494" @default.
- W2106051978 hasPublicationYear "2011" @default.
- W2106051978 type Work @default.
- W2106051978 sameAs 2106051978 @default.
- W2106051978 citedByCount "223" @default.
- W2106051978 countsByYear W21060519782012 @default.
- W2106051978 countsByYear W21060519782013 @default.
- W2106051978 countsByYear W21060519782014 @default.
- W2106051978 countsByYear W21060519782015 @default.
- W2106051978 countsByYear W21060519782016 @default.
- W2106051978 countsByYear W21060519782017 @default.
- W2106051978 countsByYear W21060519782018 @default.
- W2106051978 countsByYear W21060519782019 @default.
- W2106051978 countsByYear W21060519782020 @default.
- W2106051978 countsByYear W21060519782021 @default.
- W2106051978 countsByYear W21060519782022 @default.
- W2106051978 countsByYear W21060519782023 @default.
- W2106051978 crossrefType "proceedings-article" @default.
- W2106051978 hasAuthorship W2106051978A5024209719 @default.
- W2106051978 hasAuthorship W2106051978A5034529775 @default.
- W2106051978 hasAuthorship W2106051978A5042186348 @default.
- W2106051978 hasAuthorship W2106051978A5047062711 @default.
- W2106051978 hasAuthorship W2106051978A5070513394 @default.
- W2106051978 hasAuthorship W2106051978A5071715737 @default.
- W2106051978 hasBestOaLocation W21060519782 @default.
- W2106051978 hasConcept C108757681 @default.
- W2106051978 hasConcept C114466953 @default.
- W2106051978 hasConcept C137293760 @default.
- W2106051978 hasConcept C137546455 @default.
- W2106051978 hasConcept C138885662 @default.
- W2106051978 hasConcept C153180895 @default.
- W2106051978 hasConcept C154945302 @default.
- W2106051978 hasConcept C199360897 @default.
- W2106051978 hasConcept C23224414 @default.
- W2106051978 hasConcept C2778707766 @default.
- W2106051978 hasConcept C2778724510 @default.
- W2106051978 hasConcept C28490314 @default.
- W2106051978 hasConcept C40969351 @default.
- W2106051978 hasConcept C41008148 @default.
- W2106051978 hasConcept C41895202 @default.
- W2106051978 hasConcept C50644808 @default.
- W2106051978 hasConcept C97385483 @default.
- W2106051978 hasConcept C97931131 @default.
- W2106051978 hasConceptScore W2106051978C108757681 @default.
- W2106051978 hasConceptScore W2106051978C114466953 @default.
- W2106051978 hasConceptScore W2106051978C137293760 @default.
- W2106051978 hasConceptScore W2106051978C137546455 @default.
- W2106051978 hasConceptScore W2106051978C138885662 @default.
- W2106051978 hasConceptScore W2106051978C153180895 @default.
- W2106051978 hasConceptScore W2106051978C154945302 @default.
- W2106051978 hasConceptScore W2106051978C199360897 @default.
- W2106051978 hasConceptScore W2106051978C23224414 @default.
- W2106051978 hasConceptScore W2106051978C2778707766 @default.
- W2106051978 hasConceptScore W2106051978C2778724510 @default.
- W2106051978 hasConceptScore W2106051978C28490314 @default.
- W2106051978 hasConceptScore W2106051978C40969351 @default.
- W2106051978 hasConceptScore W2106051978C41008148 @default.
- W2106051978 hasConceptScore W2106051978C41895202 @default.
- W2106051978 hasConceptScore W2106051978C50644808 @default.
- W2106051978 hasConceptScore W2106051978C97385483 @default.
- W2106051978 hasConceptScore W2106051978C97931131 @default.
- W2106051978 hasLocation W21060519781 @default.
- W2106051978 hasLocation W21060519782 @default.
- W2106051978 hasOpenAccess W2106051978 @default.
- W2106051978 hasPrimaryLocation W21060519781 @default.
- W2106051978 hasRelatedWork W1006721676 @default.
- W2106051978 hasRelatedWork W1666710534 @default.
- W2106051978 hasRelatedWork W2080458333 @default.
- W2106051978 hasRelatedWork W2083462476 @default.
- W2106051978 hasRelatedWork W2135474356 @default.
- W2106051978 hasRelatedWork W2140027889 @default.
- W2106051978 hasRelatedWork W2143620265 @default.
- W2106051978 hasRelatedWork W2167622093 @default.
- W2106051978 hasRelatedWork W2466762647 @default.
- W2106051978 hasRelatedWork W62743518 @default.
- W2106051978 isParatext "false" @default.
- W2106051978 isRetracted "false" @default.
- W2106051978 magId "2106051978" @default.
- W2106051978 workType "article" @default.