Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896911561> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2896911561 abstract "Convolutional Neural Networks (CNNs) have been widely applied to audio classification recently where promising results have been obtained. Previous CNN-based systems mostly learn from two-dimensional time-frequency representations such as MFCC and spectrograms, which may tend to emphasize more on the background noise of the scene. To learn the key acoustic events, we introduce a three-dimensional CNN to emphasize on the different spectral characteristics from neighboring regions in spatial-temporal domain. A novel acoustic scene classification system based on multimodal deep feature fusion is proposed in this paper, where three CNNs have been presented to perform 1D raw waveform modeling, 2D time-frequency image modeling, and 3D spatial-temporal dynamics modeling, respectively. The learnt features are shown to be highly complementary to each other, which are next combined in a feature fusion network to obtain significantly improved classification predictions. Comprehensive experiments have been conducted on two large-scale acoustic scene datasets, namely the DCASE16 dataset and the LITIS Rouen dataset. Experimental results demonstrate the effectiveness of our proposed approach, as our solution achieves state-of-the-art classification rates and improves the average classification accuracy by 1.5% - 8.2% compared to the top ranked systems in the DCASE16 challenge." @default.
- W2896911561 created "2018-10-26" @default.
- W2896911561 creator A5072203134 @default.
- W2896911561 creator A5079357056 @default.
- W2896911561 creator A5082962427 @default.
- W2896911561 date "2018-10-15" @default.
- W2896911561 modified "2023-10-10" @default.
- W2896911561 title "Learning and Fusing Multimodal Deep Features for Acoustic Scene Categorization" @default.
- W2896911561 cites W1522734439 @default.
- W2896911561 cites W1994488211 @default.
- W2896911561 cites W2020770184 @default.
- W2896911561 cites W2048174296 @default.
- W2896911561 cites W2062388453 @default.
- W2896911561 cites W2095147901 @default.
- W2896911561 cites W2104657103 @default.
- W2896911561 cites W2116777898 @default.
- W2896911561 cites W2123843894 @default.
- W2896911561 cites W2142510822 @default.
- W2896911561 cites W2161565164 @default.
- W2896911561 cites W2365919995 @default.
- W2896911561 cites W2472122037 @default.
- W2896911561 cites W2511956680 @default.
- W2896911561 cites W2617002574 @default.
- W2896911561 cites W2617512665 @default.
- W2896911561 cites W2618553051 @default.
- W2896911561 cites W2619623002 @default.
- W2896911561 cites W2745969942 @default.
- W2896911561 cites W2750725664 @default.
- W2896911561 cites W3098357269 @default.
- W2896911561 doi "https://doi.org/10.1145/3240508.3240631" @default.
- W2896911561 hasPublicationYear "2018" @default.
- W2896911561 type Work @default.
- W2896911561 sameAs 2896911561 @default.
- W2896911561 citedByCount "30" @default.
- W2896911561 countsByYear W28969115612018 @default.
- W2896911561 countsByYear W28969115612019 @default.
- W2896911561 countsByYear W28969115612020 @default.
- W2896911561 countsByYear W28969115612021 @default.
- W2896911561 countsByYear W28969115612022 @default.
- W2896911561 countsByYear W28969115612023 @default.
- W2896911561 crossrefType "proceedings-article" @default.
- W2896911561 hasAuthorship W2896911561A5072203134 @default.
- W2896911561 hasAuthorship W2896911561A5079357056 @default.
- W2896911561 hasAuthorship W2896911561A5082962427 @default.
- W2896911561 hasConcept C108583219 @default.
- W2896911561 hasConcept C153180895 @default.
- W2896911561 hasConcept C154945302 @default.
- W2896911561 hasConcept C28490314 @default.
- W2896911561 hasConcept C31972630 @default.
- W2896911561 hasConcept C41008148 @default.
- W2896911561 hasConcept C94124525 @default.
- W2896911561 hasConceptScore W2896911561C108583219 @default.
- W2896911561 hasConceptScore W2896911561C153180895 @default.
- W2896911561 hasConceptScore W2896911561C154945302 @default.
- W2896911561 hasConceptScore W2896911561C28490314 @default.
- W2896911561 hasConceptScore W2896911561C31972630 @default.
- W2896911561 hasConceptScore W2896911561C41008148 @default.
- W2896911561 hasConceptScore W2896911561C94124525 @default.
- W2896911561 hasFunder F4320320751 @default.
- W2896911561 hasLocation W28969115611 @default.
- W2896911561 hasOpenAccess W2896911561 @default.
- W2896911561 hasPrimaryLocation W28969115611 @default.
- W2896911561 hasRelatedWork W2005051400 @default.
- W2896911561 hasRelatedWork W2503569529 @default.
- W2896911561 hasRelatedWork W2738221750 @default.
- W2896911561 hasRelatedWork W2773120646 @default.
- W2896911561 hasRelatedWork W3156786002 @default.
- W2896911561 hasRelatedWork W3208028783 @default.
- W2896911561 hasRelatedWork W4211209597 @default.
- W2896911561 hasRelatedWork W4245792239 @default.
- W2896911561 hasRelatedWork W3108696707 @default.
- W2896911561 hasRelatedWork W3179589182 @default.
- W2896911561 isParatext "false" @default.
- W2896911561 isRetracted "false" @default.
- W2896911561 magId "2896911561" @default.
- W2896911561 workType "article" @default.