Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285114562> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4285114562 endingPage "726" @default.
- W4285114562 startingPage "722" @default.
- W4285114562 abstract "Emotion recognition performance of deep learning models is influenced by multiple factors such as acoustic condition, textual content, style of emotion expression (e.g. acted, natural), etc. In this paper, multiple factors are analysed by training and evaluating state-of-the-art deep learning models using the input modalities speech, text, and their combination across 6 emotional speech corpora. A novel deep learning model architecture is presented that further improves the state-of-the-art in multimodal emotion recognition with speech and text on the IEMOCAP corpus. Results from models trained on individual corpora show that combining speech and text improves performance only on corpora where the text of utterances varies across different emotions, while it reduced performance on corpora with fixed text expressed in different emotions, where the speech-only models performed better. Further, cross-corpus investigations are presented to understand the robustness to changing acoustic and textual content. Results show that models perform significantly better in matched conditions in particular single corpus models perform better than multi-corpus models, with the latter showing a tendency to be more robust to acoustic variations, while performance still depends on characteristics of both training corpora and test corpus." @default.
- W4285114562 created "2022-07-14" @default.
- W4285114562 creator A5006032697 @default.
- W4285114562 creator A5062392738 @default.
- W4285114562 creator A5075928867 @default.
- W4285114562 creator A5086312107 @default.
- W4285114562 date "2022-01-01" @default.
- W4285114562 modified "2023-10-18" @default.
- W4285114562 title "Factors in Emotion Recognition With Deep Learning Models Using Speech and Text on Multiple Corpora" @default.
- W4285114562 cites W2030931454 @default.
- W4285114562 cites W2064675550 @default.
- W4285114562 cites W2146334809 @default.
- W4285114562 cites W2517617279 @default.
- W4285114562 cites W2743932329 @default.
- W4285114562 cites W2803193013 @default.
- W4285114562 cites W2899355736 @default.
- W4285114562 cites W2952073986 @default.
- W4285114562 cites W2962770129 @default.
- W4285114562 cites W2972965453 @default.
- W4285114562 cites W2973034847 @default.
- W4285114562 cites W3008554267 @default.
- W4285114562 cites W3015427680 @default.
- W4285114562 cites W3015988193 @default.
- W4285114562 cites W3096136448 @default.
- W4285114562 cites W3096690837 @default.
- W4285114562 cites W3096723250 @default.
- W4285114562 cites W3120680448 @default.
- W4285114562 cites W3136644942 @default.
- W4285114562 cites W3170774791 @default.
- W4285114562 cites W4210505096 @default.
- W4285114562 doi "https://doi.org/10.1109/lsp.2022.3151551" @default.
- W4285114562 hasPublicationYear "2022" @default.
- W4285114562 type Work @default.
- W4285114562 citedByCount "7" @default.
- W4285114562 countsByYear W42851145622022 @default.
- W4285114562 countsByYear W42851145622023 @default.
- W4285114562 crossrefType "journal-article" @default.
- W4285114562 hasAuthorship W4285114562A5006032697 @default.
- W4285114562 hasAuthorship W4285114562A5062392738 @default.
- W4285114562 hasAuthorship W4285114562A5075928867 @default.
- W4285114562 hasAuthorship W4285114562A5086312107 @default.
- W4285114562 hasConcept C104317684 @default.
- W4285114562 hasConcept C108583219 @default.
- W4285114562 hasConcept C144024400 @default.
- W4285114562 hasConcept C154945302 @default.
- W4285114562 hasConcept C185592680 @default.
- W4285114562 hasConcept C204321447 @default.
- W4285114562 hasConcept C2777438025 @default.
- W4285114562 hasConcept C2779903281 @default.
- W4285114562 hasConcept C28490314 @default.
- W4285114562 hasConcept C36289849 @default.
- W4285114562 hasConcept C41008148 @default.
- W4285114562 hasConcept C55493867 @default.
- W4285114562 hasConcept C63479239 @default.
- W4285114562 hasConceptScore W4285114562C104317684 @default.
- W4285114562 hasConceptScore W4285114562C108583219 @default.
- W4285114562 hasConceptScore W4285114562C144024400 @default.
- W4285114562 hasConceptScore W4285114562C154945302 @default.
- W4285114562 hasConceptScore W4285114562C185592680 @default.
- W4285114562 hasConceptScore W4285114562C204321447 @default.
- W4285114562 hasConceptScore W4285114562C2777438025 @default.
- W4285114562 hasConceptScore W4285114562C2779903281 @default.
- W4285114562 hasConceptScore W4285114562C28490314 @default.
- W4285114562 hasConceptScore W4285114562C36289849 @default.
- W4285114562 hasConceptScore W4285114562C41008148 @default.
- W4285114562 hasConceptScore W4285114562C55493867 @default.
- W4285114562 hasConceptScore W4285114562C63479239 @default.
- W4285114562 hasLocation W42851145621 @default.
- W4285114562 hasOpenAccess W4285114562 @default.
- W4285114562 hasPrimaryLocation W42851145621 @default.
- W4285114562 hasRelatedWork W2024146327 @default.
- W4285114562 hasRelatedWork W2731899572 @default.
- W4285114562 hasRelatedWork W2773616286 @default.
- W4285114562 hasRelatedWork W2939353110 @default.
- W4285114562 hasRelatedWork W3009238340 @default.
- W4285114562 hasRelatedWork W3215138031 @default.
- W4285114562 hasRelatedWork W4312962853 @default.
- W4285114562 hasRelatedWork W4321369474 @default.
- W4285114562 hasRelatedWork W4327774331 @default.
- W4285114562 hasRelatedWork W4360585206 @default.
- W4285114562 hasVolume "29" @default.
- W4285114562 isParatext "false" @default.
- W4285114562 isRetracted "false" @default.
- W4285114562 workType "article" @default.