FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1995562189> ?p ?o ?g. }

• W1995562189 endingPage "1545" @default.
• W1995562189 startingPage "1533" @default.
• W1995562189 abstract "Recently, the hybrid deep neural network (DNN)-hidden Markov model (HMM) has been shown to significantly improve speech recognition performance over the conventional Gaussian mixture model (GMM)-HMM. The performance improvement is partially attributed to the ability of the DNN to model complex correlations in speech features. In this paper, we show that further error rate reduction can be obtained by using convolutional neural networks (CNNs). We first present a concise description of the basic CNN and explain how it can be used for speech recognition. We further propose a limited-weight-sharing scheme that can better model speech features. The special structure such as local connectivity, weight sharing, and pooling in CNNs exhibits some degree of invariance to small shifts of speech features along the frequency axis, which is important to deal with speaker and environment variations. Experimental results show that CNNs reduce the error rate by 6%-10% compared with DNNs on the TIMIT phone recognition and the voice search large vocabulary speech recognition tasks." @default.
• W1995562189 created "2016-06-24" @default.
• W1995562189 creator A5008456610 @default.
• W1995562189 creator A5034476404 @default.
• W1995562189 creator A5035017068 @default.
• W1995562189 creator A5042186348 @default.
• W1995562189 creator A5052428595 @default.
• W1995562189 creator A5077733105 @default.
• W1995562189 date "2014-10-01" @default.
• W1995562189 modified "2023-10-17" @default.
• W1995562189 title "Convolutional Neural Networks for Speech Recognition" @default.
• W1995562189 cites W1860566644 @default.
• W1995562189 cites W1993882792 @default.
• W1995562189 cites W2012897754 @default.
• W1995562189 cites W2013598660 @default.
• W1995562189 cites W2016084804 @default.
• W1995562189 cites W2020144989 @default.
• W1995562189 cites W2022011789 @default.
• W1995562189 cites W2024539680 @default.
• W1995562189 cites W2036242736 @default.
• W1995562189 cites W2063689849 @default.
• W1995562189 cites W2074079435 @default.
• W1995562189 cites W2076794394 @default.
• W1995562189 cites W2077804127 @default.
• W1995562189 cites W2091432990 @default.
• W1995562189 cites W2101926813 @default.
• W1995562189 cites W2106051978 @default.
• W1995562189 cites W2112739286 @default.
• W1995562189 cites W2116064496 @default.
• W1995562189 cites W2117671523 @default.
• W1995562189 cites W2125964738 @default.
• W1995562189 cites W2130325614 @default.
• W1995562189 cites W2141778357 @default.
• W1995562189 cites W2147768505 @default.
• W1995562189 cites W2149600041 @default.
• W1995562189 cites W2155273149 @default.
• W1995562189 cites W2160306971 @default.
• W1995562189 cites W2160815625 @default.
• W1995562189 cites W2161742217 @default.
• W1995562189 cites W2165712214 @default.
• W1995562189 cites W2168013545 @default.
• W1995562189 cites W2172097686 @default.
• W1995562189 cites W2394932179 @default.
• W1995562189 doi "https://doi.org/10.1109/taslp.2014.2339736" @default.
• W1995562189 hasPublicationYear "2014" @default.
• W1995562189 type Work @default.
• W1995562189 sameAs 1995562189 @default.
• W1995562189 citedByCount "1635" @default.
• W1995562189 countsByYear W19955621892014 @default.
• W1995562189 countsByYear W19955621892015 @default.
• W1995562189 countsByYear W19955621892016 @default.
• W1995562189 countsByYear W19955621892017 @default.
• W1995562189 countsByYear W19955621892018 @default.
• W1995562189 countsByYear W19955621892019 @default.
• W1995562189 countsByYear W19955621892020 @default.
• W1995562189 countsByYear W19955621892021 @default.
• W1995562189 countsByYear W19955621892022 @default.
• W1995562189 countsByYear W19955621892023 @default.
• W1995562189 crossrefType "journal-article" @default.
• W1995562189 hasAuthorship W1995562189A5008456610 @default.
• W1995562189 hasAuthorship W1995562189A5034476404 @default.
• W1995562189 hasAuthorship W1995562189A5035017068 @default.
• W1995562189 hasAuthorship W1995562189A5042186348 @default.
• W1995562189 hasAuthorship W1995562189A5052428595 @default.
• W1995562189 hasAuthorship W1995562189A5077733105 @default.
• W1995562189 hasBestOaLocation W19955621892 @default.
• W1995562189 hasConcept C138885662 @default.
• W1995562189 hasConcept C153180895 @default.
• W1995562189 hasConcept C154945302 @default.
• W1995562189 hasConcept C23224414 @default.
• W1995562189 hasConcept C2777601683 @default.
• W1995562189 hasConcept C2778724510 @default.
• W1995562189 hasConcept C28490314 @default.
• W1995562189 hasConcept C40969351 @default.
• W1995562189 hasConcept C41008148 @default.
• W1995562189 hasConcept C41895202 @default.
• W1995562189 hasConcept C50644808 @default.
• W1995562189 hasConcept C70437156 @default.
• W1995562189 hasConcept C81363708 @default.
• W1995562189 hasConceptScore W1995562189C138885662 @default.
• W1995562189 hasConceptScore W1995562189C153180895 @default.
• W1995562189 hasConceptScore W1995562189C154945302 @default.
• W1995562189 hasConceptScore W1995562189C23224414 @default.
• W1995562189 hasConceptScore W1995562189C2777601683 @default.
• W1995562189 hasConceptScore W1995562189C2778724510 @default.
• W1995562189 hasConceptScore W1995562189C28490314 @default.
• W1995562189 hasConceptScore W1995562189C40969351 @default.
• W1995562189 hasConceptScore W1995562189C41008148 @default.
• W1995562189 hasConceptScore W1995562189C41895202 @default.
• W1995562189 hasConceptScore W1995562189C50644808 @default.
• W1995562189 hasConceptScore W1995562189C70437156 @default.
• W1995562189 hasConceptScore W1995562189C81363708 @default.
• W1995562189 hasIssue "10" @default.
• W1995562189 hasLocation W19955621891 @default.
• W1995562189 hasLocation W19955621892 @default.
• W1995562189 hasOpenAccess W1995562189 @default.
• W1995562189 hasPrimaryLocation W19955621891 @default.
• W1995562189 hasRelatedWork W1995562189 @default.

• next