FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1583048384> ?p ?o ?g. }

• W1583048384 abstract "This paper addresses reverberant speech recognition based on front-end processing using DAE (Deep AutoEncoder) coupled with DNN (Deep Neural Network) acoustic model. DAE can effectively and flexibly learn mapping from corrupted speech to the original clean speech based on the deep learning scheme. While this mapping is conventionally conducted only with the acoustic information, we presume the mapping is also dependent on the phone information. Therefore, we propose a new scheme (pDAE), which augments a phone-class feature to the standard acoustic features as input. Two types of the phone-class feature are investigated. One is the hard recognition result of monophones, and the other is a soft representation derived from the posterior outputs of monophone DNN. In the evaluation on the Reverb Challenge 2014 task, the augmented feature in either type results in a significant improvement (7–8% relative) from the standard DAE. It is also shown that using the soft representation in the training phase is critical." @default.
• W1583048384 created "2016-06-24" @default.
• W1583048384 creator A5023133164 @default.
• W1583048384 creator A5038044080 @default.
• W1583048384 creator A5072037248 @default.
• W1583048384 date "2015-04-01" @default.
• W1583048384 modified "2023-09-23" @default.
• W1583048384 title "Deep autoencoders augmented with phone-class feature for reverberant speech recognition" @default.
• W1583048384 cites W1973681148 @default.
• W1583048384 cites W1989314204 @default.
• W1583048384 cites W1993882792 @default.
• W1583048384 cites W2022011789 @default.
• W1583048384 cites W2025768430 @default.
• W1583048384 cites W2054566816 @default.
• W1583048384 cites W2062164080 @default.
• W1583048384 cites W2079623482 @default.
• W1583048384 cites W2082474452 @default.
• W1583048384 cites W2085313529 @default.
• W1583048384 cites W2089177488 @default.
• W1583048384 cites W2100432131 @default.
• W1583048384 cites W2100495367 @default.
• W1583048384 cites W2106259503 @default.
• W1583048384 cites W2107992675 @default.
• W1583048384 cites W2110322414 @default.
• W1583048384 cites W2110798204 @default.
• W1583048384 cites W2130640611 @default.
• W1583048384 cites W2146871184 @default.
• W1583048384 cites W2147768505 @default.
• W1583048384 cites W2157649472 @default.
• W1583048384 cites W2160815625 @default.
• W1583048384 cites W2168013545 @default.
• W1583048384 cites W2184045248 @default.
• W1583048384 cites W2296581541 @default.
• W1583048384 cites W2394932179 @default.
• W1583048384 cites W2403307129 @default.
• W1583048384 cites W2405774341 @default.
• W1583048384 cites W2408660648 @default.
• W1583048384 cites W2408713104 @default.
• W1583048384 doi "https://doi.org/10.1109/icassp.2015.7178795" @default.
• W1583048384 hasPublicationYear "2015" @default.
• W1583048384 type Work @default.
• W1583048384 sameAs 1583048384 @default.
• W1583048384 citedByCount "14" @default.
• W1583048384 countsByYear W15830483842015 @default.
• W1583048384 countsByYear W15830483842016 @default.
• W1583048384 countsByYear W15830483842017 @default.
• W1583048384 countsByYear W15830483842018 @default.
• W1583048384 countsByYear W15830483842019 @default.
• W1583048384 countsByYear W15830483842020 @default.
• W1583048384 countsByYear W15830483842021 @default.
• W1583048384 crossrefType "proceedings-article" @default.
• W1583048384 hasAuthorship W1583048384A5023133164 @default.
• W1583048384 hasAuthorship W1583048384A5038044080 @default.
• W1583048384 hasAuthorship W1583048384A5072037248 @default.
• W1583048384 hasConcept C101738243 @default.
• W1583048384 hasConcept C108583219 @default.
• W1583048384 hasConcept C134306372 @default.
• W1583048384 hasConcept C138885662 @default.
• W1583048384 hasConcept C153180895 @default.
• W1583048384 hasConcept C154945302 @default.
• W1583048384 hasConcept C17744445 @default.
• W1583048384 hasConcept C199539241 @default.
• W1583048384 hasConcept C2776359362 @default.
• W1583048384 hasConcept C2776401178 @default.
• W1583048384 hasConcept C2777212361 @default.
• W1583048384 hasConcept C2778707766 @default.
• W1583048384 hasConcept C28490314 @default.
• W1583048384 hasConcept C2984842247 @default.
• W1583048384 hasConcept C33923547 @default.
• W1583048384 hasConcept C41008148 @default.
• W1583048384 hasConcept C41895202 @default.
• W1583048384 hasConcept C50644808 @default.
• W1583048384 hasConcept C52622490 @default.
• W1583048384 hasConcept C59404180 @default.
• W1583048384 hasConcept C77618280 @default.
• W1583048384 hasConcept C94625758 @default.
• W1583048384 hasConceptScore W1583048384C101738243 @default.
• W1583048384 hasConceptScore W1583048384C108583219 @default.
• W1583048384 hasConceptScore W1583048384C134306372 @default.
• W1583048384 hasConceptScore W1583048384C138885662 @default.
• W1583048384 hasConceptScore W1583048384C153180895 @default.
• W1583048384 hasConceptScore W1583048384C154945302 @default.
• W1583048384 hasConceptScore W1583048384C17744445 @default.
• W1583048384 hasConceptScore W1583048384C199539241 @default.
• W1583048384 hasConceptScore W1583048384C2776359362 @default.
• W1583048384 hasConceptScore W1583048384C2776401178 @default.
• W1583048384 hasConceptScore W1583048384C2777212361 @default.
• W1583048384 hasConceptScore W1583048384C2778707766 @default.
• W1583048384 hasConceptScore W1583048384C28490314 @default.
• W1583048384 hasConceptScore W1583048384C2984842247 @default.
• W1583048384 hasConceptScore W1583048384C33923547 @default.
• W1583048384 hasConceptScore W1583048384C41008148 @default.
• W1583048384 hasConceptScore W1583048384C41895202 @default.
• W1583048384 hasConceptScore W1583048384C50644808 @default.
• W1583048384 hasConceptScore W1583048384C52622490 @default.
• W1583048384 hasConceptScore W1583048384C59404180 @default.
• W1583048384 hasConceptScore W1583048384C77618280 @default.
• W1583048384 hasConceptScore W1583048384C94625758 @default.
• W1583048384 hasLocation W15830483841 @default.
• W1583048384 hasOpenAccess W1583048384 @default.

• next