FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891436445> ?p ?o ?g. }

• W2891436445 abstract "Prior knowledge of the relative transfer function (RTF) is useful in many applications but remains little studied. In this paper, we propose a semi-supervised learning algorithm based on deep neural networks (DNNs) for RTF inverse regression, that is to generate the full-band RTF vector directly from the source-receiver pose (position and orientation). Two typical scenarios are discussed: training on labeled RTFs only, or on additional unlabeled RTFs. Both setups utilize the low-dimensional manifold property of RTF in stationary environments. With this property as an additional regularization term, a smooth mapping solution with respect to the manifold is obtained. Experimental simulations show that the proposed method achieves a lower mean prediction error than the free field model with few labeled RTFs, and the unlabeled RTFs are essential in improving the inverse regression performance." @default.
• W2891436445 created "2018-09-27" @default.
• W2891436445 creator A5040424136 @default.
• W2891436445 creator A5065635001 @default.
• W2891436445 creator A5066595006 @default.
• W2891436445 creator A5082789515 @default.
• W2891436445 date "2018-04-01" @default.
• W2891436445 modified "2023-09-27" @default.
• W2891436445 title "Semi-Supervised Learning with Deep Neural Networks for Relative Transfer Function Inverse Regression" @default.
• W2891436445 cites W1772191655 @default.
• W2891436445 cites W1811954879 @default.
• W2891436445 cites W1981463705 @default.
• W2891436445 cites W1994654142 @default.
• W2891436445 cites W2000062601 @default.
• W2891436445 cites W2066853009 @default.
• W2891436445 cites W2086356052 @default.
• W2891436445 cites W2087945031 @default.
• W2891436445 cites W2115969105 @default.
• W2891436445 cites W2117678320 @default.
• W2891436445 cites W2135158232 @default.
• W2891436445 cites W2147665979 @default.
• W2891436445 cites W2156676906 @default.
• W2891436445 cites W2568308529 @default.
• W2891436445 cites W3100871498 @default.
• W2891436445 doi "https://doi.org/10.1109/icassp.2018.8462639" @default.
• W2891436445 hasPublicationYear "2018" @default.
• W2891436445 type Work @default.
• W2891436445 sameAs 2891436445 @default.
• W2891436445 citedByCount "4" @default.
• W2891436445 countsByYear W28914364452021 @default.
• W2891436445 countsByYear W28914364452022 @default.
• W2891436445 crossrefType "proceedings-article" @default.
• W2891436445 hasAuthorship W2891436445A5040424136 @default.
• W2891436445 hasAuthorship W2891436445A5065635001 @default.
• W2891436445 hasAuthorship W2891436445A5066595006 @default.
• W2891436445 hasAuthorship W2891436445A5082789515 @default.
• W2891436445 hasBestOaLocation W28914364452 @default.
• W2891436445 hasConcept C10138342 @default.
• W2891436445 hasConcept C105795698 @default.
• W2891436445 hasConcept C111472728 @default.
• W2891436445 hasConcept C11413529 @default.
• W2891436445 hasConcept C119599485 @default.
• W2891436445 hasConcept C127413603 @default.
• W2891436445 hasConcept C134306372 @default.
• W2891436445 hasConcept C135252773 @default.
• W2891436445 hasConcept C138885662 @default.
• W2891436445 hasConcept C154945302 @default.
• W2891436445 hasConcept C162324750 @default.
• W2891436445 hasConcept C189950617 @default.
• W2891436445 hasConcept C198082294 @default.
• W2891436445 hasConcept C207467116 @default.
• W2891436445 hasConcept C2524010 @default.
• W2891436445 hasConcept C2776135515 @default.
• W2891436445 hasConcept C33923547 @default.
• W2891436445 hasConcept C41008148 @default.
• W2891436445 hasConcept C50644808 @default.
• W2891436445 hasConcept C529865628 @default.
• W2891436445 hasConcept C78519656 @default.
• W2891436445 hasConcept C81299745 @default.
• W2891436445 hasConcept C83546350 @default.
• W2891436445 hasConceptScore W2891436445C10138342 @default.
• W2891436445 hasConceptScore W2891436445C105795698 @default.
• W2891436445 hasConceptScore W2891436445C111472728 @default.
• W2891436445 hasConceptScore W2891436445C11413529 @default.
• W2891436445 hasConceptScore W2891436445C119599485 @default.
• W2891436445 hasConceptScore W2891436445C127413603 @default.
• W2891436445 hasConceptScore W2891436445C134306372 @default.
• W2891436445 hasConceptScore W2891436445C135252773 @default.
• W2891436445 hasConceptScore W2891436445C138885662 @default.
• W2891436445 hasConceptScore W2891436445C154945302 @default.
• W2891436445 hasConceptScore W2891436445C162324750 @default.
• W2891436445 hasConceptScore W2891436445C189950617 @default.
• W2891436445 hasConceptScore W2891436445C198082294 @default.
• W2891436445 hasConceptScore W2891436445C207467116 @default.
• W2891436445 hasConceptScore W2891436445C2524010 @default.
• W2891436445 hasConceptScore W2891436445C2776135515 @default.
• W2891436445 hasConceptScore W2891436445C33923547 @default.
• W2891436445 hasConceptScore W2891436445C41008148 @default.
• W2891436445 hasConceptScore W2891436445C50644808 @default.
• W2891436445 hasConceptScore W2891436445C529865628 @default.
• W2891436445 hasConceptScore W2891436445C78519656 @default.
• W2891436445 hasConceptScore W2891436445C81299745 @default.
• W2891436445 hasConceptScore W2891436445C83546350 @default.
• W2891436445 hasLocation W28914364451 @default.
• W2891436445 hasLocation W28914364452 @default.
• W2891436445 hasLocation W28914364453 @default.
• W2891436445 hasOpenAccess W2891436445 @default.
• W2891436445 hasPrimaryLocation W28914364451 @default.
• W2891436445 hasRelatedWork W1933951994 @default.
• W2891436445 hasRelatedWork W1975931727 @default.
• W2891436445 hasRelatedWork W1980515350 @default.
• W2891436445 hasRelatedWork W2046055439 @default.
• W2891436445 hasRelatedWork W2086268342 @default.
• W2891436445 hasRelatedWork W2799167307 @default.
• W2891436445 hasRelatedWork W3035984619 @default.
• W2891436445 hasRelatedWork W3132948797 @default.
• W2891436445 hasRelatedWork W4298143267 @default.
• W2891436445 hasRelatedWork W4300278971 @default.
• W2891436445 isParatext "false" @default.
• W2891436445 isRetracted "false" @default.

• next