Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891627435> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2891627435 abstract "This paper describes an unsupervised adaptation method of deep neural networks (DNNs) regarding discriminative sound source localization (SSL). DNNs-based SSL and its unsupervised adaptation fail under different conditions from those during training. The estimations sometimes include incoherent unpredictable errors due to the NN's non-linearity. We propose an eliminative posterior probability constraint using a model-based SSL for unsupervised DNNs adaptation. This constraint forces the probability of “less possible candidates” to become zero to eliminate incoherent errors. The candidates are indicated by a model-based SSL method because it can estimate the azimuth of the sound source with moderate accuracy and explicit reasoning. As a result, the localization performance of adapted DNNs improved more than that of model-based SSL. Experimental results showed that our method improved localization correctness of 1D azimuth and 3D regions by a maximum of 13.3 and 5.9 points compared with the model-based SSL." @default.
- W2891627435 created "2018-09-27" @default.
- W2891627435 creator A5024093607 @default.
- W2891627435 creator A5026275950 @default.
- W2891627435 creator A5036701229 @default.
- W2891627435 creator A5049614400 @default.
- W2891627435 creator A5052000885 @default.
- W2891627435 date "2018-04-01" @default.
- W2891627435 modified "2023-10-02" @default.
- W2891627435 title "Unsupervised Adaptation of Neural Networks for Discriminative Sound Source Localization with Eliminative Constraint" @default.
- W2891627435 cites W1989000345 @default.
- W2891627435 cites W1998924366 @default.
- W2891627435 cites W2024897398 @default.
- W2891627435 cites W2080005694 @default.
- W2891627435 cites W2131474463 @default.
- W2891627435 cites W2162654459 @default.
- W2891627435 cites W2403149086 @default.
- W2891627435 cites W2586642235 @default.
- W2891627435 cites W2592109325 @default.
- W2891627435 doi "https://doi.org/10.1109/icassp.2018.8461723" @default.
- W2891627435 hasPublicationYear "2018" @default.
- W2891627435 type Work @default.
- W2891627435 sameAs 2891627435 @default.
- W2891627435 citedByCount "11" @default.
- W2891627435 countsByYear W28916274352019 @default.
- W2891627435 countsByYear W28916274352020 @default.
- W2891627435 countsByYear W28916274352021 @default.
- W2891627435 countsByYear W28916274352022 @default.
- W2891627435 countsByYear W28916274352023 @default.
- W2891627435 crossrefType "proceedings-article" @default.
- W2891627435 hasAuthorship W2891627435A5024093607 @default.
- W2891627435 hasAuthorship W2891627435A5026275950 @default.
- W2891627435 hasAuthorship W2891627435A5036701229 @default.
- W2891627435 hasAuthorship W2891627435A5049614400 @default.
- W2891627435 hasAuthorship W2891627435A5052000885 @default.
- W2891627435 hasConcept C11413529 @default.
- W2891627435 hasConcept C120665830 @default.
- W2891627435 hasConcept C121332964 @default.
- W2891627435 hasConcept C139807058 @default.
- W2891627435 hasConcept C153180895 @default.
- W2891627435 hasConcept C154945302 @default.
- W2891627435 hasConcept C159737794 @default.
- W2891627435 hasConcept C2524010 @default.
- W2891627435 hasConcept C2776036281 @default.
- W2891627435 hasConcept C28490314 @default.
- W2891627435 hasConcept C2984842247 @default.
- W2891627435 hasConcept C33923547 @default.
- W2891627435 hasConcept C41008148 @default.
- W2891627435 hasConcept C50644808 @default.
- W2891627435 hasConcept C55439883 @default.
- W2891627435 hasConcept C8038995 @default.
- W2891627435 hasConcept C97931131 @default.
- W2891627435 hasConceptScore W2891627435C11413529 @default.
- W2891627435 hasConceptScore W2891627435C120665830 @default.
- W2891627435 hasConceptScore W2891627435C121332964 @default.
- W2891627435 hasConceptScore W2891627435C139807058 @default.
- W2891627435 hasConceptScore W2891627435C153180895 @default.
- W2891627435 hasConceptScore W2891627435C154945302 @default.
- W2891627435 hasConceptScore W2891627435C159737794 @default.
- W2891627435 hasConceptScore W2891627435C2524010 @default.
- W2891627435 hasConceptScore W2891627435C2776036281 @default.
- W2891627435 hasConceptScore W2891627435C28490314 @default.
- W2891627435 hasConceptScore W2891627435C2984842247 @default.
- W2891627435 hasConceptScore W2891627435C33923547 @default.
- W2891627435 hasConceptScore W2891627435C41008148 @default.
- W2891627435 hasConceptScore W2891627435C50644808 @default.
- W2891627435 hasConceptScore W2891627435C55439883 @default.
- W2891627435 hasConceptScore W2891627435C8038995 @default.
- W2891627435 hasConceptScore W2891627435C97931131 @default.
- W2891627435 hasLocation W28916274351 @default.
- W2891627435 hasOpenAccess W2891627435 @default.
- W2891627435 hasPrimaryLocation W28916274351 @default.
- W2891627435 hasRelatedWork W1972656095 @default.
- W2891627435 hasRelatedWork W2024160000 @default.
- W2891627435 hasRelatedWork W2061273563 @default.
- W2891627435 hasRelatedWork W2285052147 @default.
- W2891627435 hasRelatedWork W2729514902 @default.
- W2891627435 hasRelatedWork W2743258233 @default.
- W2891627435 hasRelatedWork W2773500201 @default.
- W2891627435 hasRelatedWork W2970216048 @default.
- W2891627435 hasRelatedWork W2998168123 @default.
- W2891627435 hasRelatedWork W4287995534 @default.
- W2891627435 isParatext "false" @default.
- W2891627435 isRetracted "false" @default.
- W2891627435 magId "2891627435" @default.
- W2891627435 workType "article" @default.