Matches in SemOpenAlex for { <https://semopenalex.org/work/W2289120528> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2289120528 abstract "Bottleneck (BN) features, particularly based on deep structures of a neural network, have been successfully applied to Automatic Speech Recognition (ASR) tasks. This paper goes on the study of improving the BN features for ASR tasks by employing two different methods: (1) a Cochleagram generated by Gammatone filters as the input feature for a deep neural network; (2) imposing the sparsity regularization on the bottleneck layer to control the sparsity level of BN features by constraining the activations of the hidden units to be averagely inactive most of the time. Our experiments on the Wall Street Journal (WSJ) database demonstrate that the two approaches can deliver certain performance gains to BN features for ASR tasks. In addition, further experiments on the WSJ database from different noise levels show that the Cochleagram as input has better noise-robust performance than the commonly used Mel-scaled filterbank." @default.
- W2289120528 created "2016-06-24" @default.
- W2289120528 creator A5034981144 @default.
- W2289120528 creator A5036455193 @default.
- W2289120528 creator A5042520842 @default.
- W2289120528 creator A5062665642 @default.
- W2289120528 date "2015-12-01" @default.
- W2289120528 modified "2023-10-06" @default.
- W2289120528 title "Improving bottleneck features for automatic speech recognition using gammatone-based cochleagram and sparsity regularization" @default.
- W2289120528 cites W111666610 @default.
- W2289120528 cites W1524333225 @default.
- W2289120528 cites W1663973292 @default.
- W2289120528 cites W179430498 @default.
- W2289120528 cites W197151588 @default.
- W2289120528 cites W2012897754 @default.
- W2289120528 cites W2100495367 @default.
- W2289120528 cites W2123237149 @default.
- W2289120528 cites W2160815625 @default.
- W2289120528 cites W2184045248 @default.
- W2289120528 cites W2400101145 @default.
- W2289120528 cites W2401449658 @default.
- W2289120528 cites W1490216641 @default.
- W2289120528 doi "https://doi.org/10.1109/apsipa.2015.7415401" @default.
- W2289120528 hasPublicationYear "2015" @default.
- W2289120528 type Work @default.
- W2289120528 sameAs 2289120528 @default.
- W2289120528 citedByCount "1" @default.
- W2289120528 countsByYear W22891205282020 @default.
- W2289120528 crossrefType "proceedings-article" @default.
- W2289120528 hasAuthorship W2289120528A5034981144 @default.
- W2289120528 hasAuthorship W2289120528A5036455193 @default.
- W2289120528 hasAuthorship W2289120528A5042520842 @default.
- W2289120528 hasAuthorship W2289120528A5062665642 @default.
- W2289120528 hasConcept C100515483 @default.
- W2289120528 hasConcept C106131492 @default.
- W2289120528 hasConcept C115961682 @default.
- W2289120528 hasConcept C138885662 @default.
- W2289120528 hasConcept C149635348 @default.
- W2289120528 hasConcept C153180895 @default.
- W2289120528 hasConcept C154945302 @default.
- W2289120528 hasConcept C23224414 @default.
- W2289120528 hasConcept C2776135515 @default.
- W2289120528 hasConcept C2776401178 @default.
- W2289120528 hasConcept C2780513914 @default.
- W2289120528 hasConcept C28490314 @default.
- W2289120528 hasConcept C31972630 @default.
- W2289120528 hasConcept C41008148 @default.
- W2289120528 hasConcept C41895202 @default.
- W2289120528 hasConcept C50644808 @default.
- W2289120528 hasConcept C52622490 @default.
- W2289120528 hasConcept C99498987 @default.
- W2289120528 hasConceptScore W2289120528C100515483 @default.
- W2289120528 hasConceptScore W2289120528C106131492 @default.
- W2289120528 hasConceptScore W2289120528C115961682 @default.
- W2289120528 hasConceptScore W2289120528C138885662 @default.
- W2289120528 hasConceptScore W2289120528C149635348 @default.
- W2289120528 hasConceptScore W2289120528C153180895 @default.
- W2289120528 hasConceptScore W2289120528C154945302 @default.
- W2289120528 hasConceptScore W2289120528C23224414 @default.
- W2289120528 hasConceptScore W2289120528C2776135515 @default.
- W2289120528 hasConceptScore W2289120528C2776401178 @default.
- W2289120528 hasConceptScore W2289120528C2780513914 @default.
- W2289120528 hasConceptScore W2289120528C28490314 @default.
- W2289120528 hasConceptScore W2289120528C31972630 @default.
- W2289120528 hasConceptScore W2289120528C41008148 @default.
- W2289120528 hasConceptScore W2289120528C41895202 @default.
- W2289120528 hasConceptScore W2289120528C50644808 @default.
- W2289120528 hasConceptScore W2289120528C52622490 @default.
- W2289120528 hasConceptScore W2289120528C99498987 @default.
- W2289120528 hasLocation W22891205281 @default.
- W2289120528 hasOpenAccess W2289120528 @default.
- W2289120528 hasPrimaryLocation W22891205281 @default.
- W2289120528 hasRelatedWork W1563317239 @default.
- W2289120528 hasRelatedWork W1991904167 @default.
- W2289120528 hasRelatedWork W2145830023 @default.
- W2289120528 hasRelatedWork W2149827538 @default.
- W2289120528 hasRelatedWork W2295047066 @default.
- W2289120528 hasRelatedWork W2493711915 @default.
- W2289120528 hasRelatedWork W2508627142 @default.
- W2289120528 hasRelatedWork W2566553956 @default.
- W2289120528 hasRelatedWork W2583851971 @default.
- W2289120528 hasRelatedWork W2600349216 @default.
- W2289120528 hasRelatedWork W2782900155 @default.
- W2289120528 hasRelatedWork W2791927058 @default.
- W2289120528 hasRelatedWork W2900915105 @default.
- W2289120528 hasRelatedWork W2979324980 @default.
- W2289120528 hasRelatedWork W2995653082 @default.
- W2289120528 hasRelatedWork W3034535039 @default.
- W2289120528 hasRelatedWork W3114831946 @default.
- W2289120528 hasRelatedWork W3134293379 @default.
- W2289120528 hasRelatedWork W3184180254 @default.
- W2289120528 hasRelatedWork W2772561196 @default.
- W2289120528 isParatext "false" @default.
- W2289120528 isRetracted "false" @default.
- W2289120528 magId "2289120528" @default.
- W2289120528 workType "article" @default.