Matches in SemOpenAlex for { <https://semopenalex.org/work/W3083173864> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3083173864 endingPage "16" @default.
- W3083173864 startingPage "1" @default.
- W3083173864 abstract "For human-like agents, including virtual avatars and social robots, making proper gestures while speaking is crucial in human--agent interaction. Co-speech gestures enhance interaction experiences and make the agents look alive. However, it is difficult to generate human-like gestures due to the lack of understanding of how people gesture. Data-driven approaches attempt to learn gesticulation skills from human demonstrations, but the ambiguous and individual nature of gestures hinders learning. In this paper, we present an automatic gesture generation model that uses the multimodal context of speech text, audio, and speaker identity to reliably generate gestures. By incorporating a multimodal context and an adversarial training scheme, the proposed model outputs gestures that are human-like and that match with speech content and rhythm. We also introduce a new quantitative evaluation metric for gesture generation models. Experiments with the introduced metric and subjective human evaluation showed that the proposed gesture generation model is better than existing end-to-end generation models. We further confirm that our model is able to work with synthesized audio in a scenario where contexts are constrained, and show that different gesture styles can be generated for the same speech by specifying different speaker identities in the style embedding space that is learned from videos of various speakers. All the code and data is available at https://github.com/ai4r/Gesture-Generation-from-Trimodal-Context." @default.
- W3083173864 created "2020-09-11" @default.
- W3083173864 creator A5009537165 @default.
- W3083173864 creator A5034140846 @default.
- W3083173864 creator A5034953122 @default.
- W3083173864 creator A5037673037 @default.
- W3083173864 creator A5045112037 @default.
- W3083173864 creator A5059564500 @default.
- W3083173864 creator A5069073713 @default.
- W3083173864 date "2020-12-31" @default.
- W3083173864 modified "2023-10-17" @default.
- W3083173864 title "Speech gesture generation from the trimodal context of text, audio, and speaker identity" @default.
- W3083173864 cites W1969681536 @default.
- W3083173864 cites W1973282202 @default.
- W3083173864 cites W2046033161 @default.
- W3083173864 cites W2061009502 @default.
- W3083173864 cites W2081580037 @default.
- W3083173864 cites W2101032778 @default.
- W3083173864 cites W2135431835 @default.
- W3083173864 cites W2201822004 @default.
- W3083173864 cites W2250539671 @default.
- W3083173864 cites W2296371640 @default.
- W3083173864 cites W2493916176 @default.
- W3083173864 cites W2495266147 @default.
- W3083173864 cites W2619383789 @default.
- W3083173864 cites W2962785568 @default.
- W3083173864 cites W2962896489 @default.
- W3083173864 cites W2963185411 @default.
- W3083173864 cites W2963544341 @default.
- W3083173864 cites W2981802563 @default.
- W3083173864 cites W2982625143 @default.
- W3083173864 cites W3048625561 @default.
- W3083173864 doi "https://doi.org/10.1145/3414685.3417838" @default.
- W3083173864 hasPublicationYear "2020" @default.
- W3083173864 type Work @default.
- W3083173864 sameAs 3083173864 @default.
- W3083173864 citedByCount "105" @default.
- W3083173864 countsByYear W30831738642021 @default.
- W3083173864 countsByYear W30831738642022 @default.
- W3083173864 countsByYear W30831738642023 @default.
- W3083173864 crossrefType "journal-article" @default.
- W3083173864 hasAuthorship W3083173864A5009537165 @default.
- W3083173864 hasAuthorship W3083173864A5034140846 @default.
- W3083173864 hasAuthorship W3083173864A5034953122 @default.
- W3083173864 hasAuthorship W3083173864A5037673037 @default.
- W3083173864 hasAuthorship W3083173864A5045112037 @default.
- W3083173864 hasAuthorship W3083173864A5059564500 @default.
- W3083173864 hasAuthorship W3083173864A5069073713 @default.
- W3083173864 hasBestOaLocation W30831738641 @default.
- W3083173864 hasConcept C107457646 @default.
- W3083173864 hasConcept C121332964 @default.
- W3083173864 hasConcept C151730666 @default.
- W3083173864 hasConcept C154945302 @default.
- W3083173864 hasConcept C159437735 @default.
- W3083173864 hasConcept C204321447 @default.
- W3083173864 hasConcept C207347870 @default.
- W3083173864 hasConcept C24890656 @default.
- W3083173864 hasConcept C2778355321 @default.
- W3083173864 hasConcept C2779343474 @default.
- W3083173864 hasConcept C28490314 @default.
- W3083173864 hasConcept C41008148 @default.
- W3083173864 hasConcept C41608201 @default.
- W3083173864 hasConcept C86803240 @default.
- W3083173864 hasConceptScore W3083173864C107457646 @default.
- W3083173864 hasConceptScore W3083173864C121332964 @default.
- W3083173864 hasConceptScore W3083173864C151730666 @default.
- W3083173864 hasConceptScore W3083173864C154945302 @default.
- W3083173864 hasConceptScore W3083173864C159437735 @default.
- W3083173864 hasConceptScore W3083173864C204321447 @default.
- W3083173864 hasConceptScore W3083173864C207347870 @default.
- W3083173864 hasConceptScore W3083173864C24890656 @default.
- W3083173864 hasConceptScore W3083173864C2778355321 @default.
- W3083173864 hasConceptScore W3083173864C2779343474 @default.
- W3083173864 hasConceptScore W3083173864C28490314 @default.
- W3083173864 hasConceptScore W3083173864C41008148 @default.
- W3083173864 hasConceptScore W3083173864C41608201 @default.
- W3083173864 hasConceptScore W3083173864C86803240 @default.
- W3083173864 hasIssue "6" @default.
- W3083173864 hasLocation W30831738641 @default.
- W3083173864 hasLocation W30831738642 @default.
- W3083173864 hasOpenAccess W3083173864 @default.
- W3083173864 hasPrimaryLocation W30831738641 @default.
- W3083173864 hasRelatedWork W1974238679 @default.
- W3083173864 hasRelatedWork W2031784641 @default.
- W3083173864 hasRelatedWork W2507962226 @default.
- W3083173864 hasRelatedWork W2543128534 @default.
- W3083173864 hasRelatedWork W2739074143 @default.
- W3083173864 hasRelatedWork W3105536343 @default.
- W3083173864 hasRelatedWork W4253137324 @default.
- W3083173864 hasRelatedWork W4284992834 @default.
- W3083173864 hasRelatedWork W2187794806 @default.
- W3083173864 hasRelatedWork W2559993915 @default.
- W3083173864 hasVolume "39" @default.
- W3083173864 isParatext "false" @default.
- W3083173864 isRetracted "false" @default.
- W3083173864 magId "3083173864" @default.
- W3083173864 workType "article" @default.