FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309969805> ?p ?o ?g. }

• W4309969805 abstract "Speech emotion recognition systems use data-driven machine learning techniques that rely on annotated corpora. To achieve a usable performance in real-life, we need to exploit multiple different datasets since each one can shed the light on some specific expression of affect. However, different corpora use subjectively defined annotation schemes, which poses a challenge to train a model that can sense similar emotions across different corpora. Here, we propose a method that can relate similar emotions across corpora without being explicitly trained for it. Our method relies on self-supervised representations, which can provide us with highly contextualised speech representations, and multi-task learning paradigms. This allows to train on different corpora without changing their labelling schemes. The results show that by fine-tuning self-supervised representations on each corpus separately, we can significantly improve the state of the art within-corpus performance. We further demonstrate that by using multiple corpora during the training of the same model, we can improve the cross-corpus performance, and show that our emotion embeddings can effectively recognise the same emotions across different corpora." @default.
• W4309969805 created "2022-11-30" @default.
• W4309969805 creator A5026933067 @default.
• W4309969805 creator A5061577777 @default.
• W4309969805 creator A5079066445 @default.
• W4309969805 date "2022-10-18" @default.
• W4309969805 modified "2023-09-25" @default.
• W4309969805 title "Multi-Corpus Affect Recognition with Emotion Embeddings and Self-Supervised Representations of Speech" @default.
• W4309969805 cites W175750906 @default.
• W4309969805 cites W1966797434 @default.
• W4309969805 cites W2045528981 @default.
• W4309969805 cites W2149628368 @default.
• W4309969805 cites W2329093554 @default.
• W4309969805 cites W2343758848 @default.
• W4309969805 cites W2680534654 @default.
• W4309969805 cites W2747172199 @default.
• W4309969805 cites W2787322890 @default.
• W4309969805 cites W2803193013 @default.
• W4309969805 cites W2810556878 @default.
• W4309969805 cites W2888731576 @default.
• W4309969805 cites W2939274787 @default.
• W4309969805 cites W2946218857 @default.
• W4309969805 cites W2963087748 @default.
• W4309969805 cites W2981677410 @default.
• W4309969805 cites W3015141382 @default.
• W4309969805 cites W3020211967 @default.
• W4309969805 cites W3096690837 @default.
• W4309969805 cites W3097936578 @default.
• W4309969805 cites W3126625480 @default.
• W4309969805 cites W3137890092 @default.
• W4309969805 cites W3189296823 @default.
• W4309969805 cites W3197078573 @default.
• W4309969805 cites W3197642003 @default.
• W4309969805 cites W3197994565 @default.
• W4309969805 cites W3198771897 @default.
• W4309969805 cites W3208332648 @default.
• W4309969805 cites W3208439161 @default.
• W4309969805 cites W4210505096 @default.
• W4309969805 cites W4210796791 @default.
• W4309969805 cites W4248172427 @default.
• W4309969805 cites W3161933272 @default.
• W4309969805 doi "https://doi.org/10.1109/acii55700.2022.9953840" @default.
• W4309969805 hasPublicationYear "2022" @default.
• W4309969805 type Work @default.
• W4309969805 citedByCount "2" @default.
• W4309969805 countsByYear W43099698052023 @default.
• W4309969805 crossrefType "proceedings-article" @default.
• W4309969805 hasAuthorship W4309969805A5026933067 @default.
• W4309969805 hasAuthorship W4309969805A5061577777 @default.
• W4309969805 hasAuthorship W4309969805A5079066445 @default.
• W4309969805 hasBestOaLocation W43099698052 @default.
• W4309969805 hasConcept C136764020 @default.
• W4309969805 hasConcept C138885662 @default.
• W4309969805 hasConcept C154945302 @default.
• W4309969805 hasConcept C162324750 @default.
• W4309969805 hasConcept C165696696 @default.
• W4309969805 hasConcept C187736073 @default.
• W4309969805 hasConcept C204321447 @default.
• W4309969805 hasConcept C2776035688 @default.
• W4309969805 hasConcept C2776145971 @default.
• W4309969805 hasConcept C2776321320 @default.
• W4309969805 hasConcept C2780451532 @default.
• W4309969805 hasConcept C2780615836 @default.
• W4309969805 hasConcept C28490314 @default.
• W4309969805 hasConcept C38652104 @default.
• W4309969805 hasConcept C41008148 @default.
• W4309969805 hasConcept C41895202 @default.
• W4309969805 hasConceptScore W4309969805C136764020 @default.
• W4309969805 hasConceptScore W4309969805C138885662 @default.
• W4309969805 hasConceptScore W4309969805C154945302 @default.
• W4309969805 hasConceptScore W4309969805C162324750 @default.
• W4309969805 hasConceptScore W4309969805C165696696 @default.
• W4309969805 hasConceptScore W4309969805C187736073 @default.
• W4309969805 hasConceptScore W4309969805C204321447 @default.
• W4309969805 hasConceptScore W4309969805C2776035688 @default.
• W4309969805 hasConceptScore W4309969805C2776145971 @default.
• W4309969805 hasConceptScore W4309969805C2776321320 @default.
• W4309969805 hasConceptScore W4309969805C2780451532 @default.
• W4309969805 hasConceptScore W4309969805C2780615836 @default.
• W4309969805 hasConceptScore W4309969805C28490314 @default.
• W4309969805 hasConceptScore W4309969805C38652104 @default.
• W4309969805 hasConceptScore W4309969805C41008148 @default.
• W4309969805 hasConceptScore W4309969805C41895202 @default.
• W4309969805 hasFunder F4320321663 @default.
• W4309969805 hasLocation W43099698051 @default.
• W4309969805 hasLocation W43099698052 @default.
• W4309969805 hasOpenAccess W4309969805 @default.
• W4309969805 hasPrimaryLocation W43099698051 @default.
• W4309969805 hasRelatedWork W1529400504 @default.
• W4309969805 hasRelatedWork W1596397513 @default.
• W4309969805 hasRelatedWork W1607315280 @default.
• W4309969805 hasRelatedWork W1892467659 @default.
• W4309969805 hasRelatedWork W2331043530 @default.
• W4309969805 hasRelatedWork W2374725260 @default.
• W4309969805 hasRelatedWork W2383403914 @default.
• W4309969805 hasRelatedWork W2393933887 @default.
• W4309969805 hasRelatedWork W2997512100 @default.
• W4309969805 hasRelatedWork W97423259 @default.
• W4309969805 isParatext "false" @default.
• W4309969805 isRetracted "false" @default.

• next