Matches in Ghent University Academic Bibliography for { <https://biblio.ugent.be/publication/01HF4Q7521P5877H6PZFEWYSS3> ?p ?o. }
Showing items 1 to 21 of
21
with 100 items per page.
- 01HF4Q7521P5877H6PZFEWYSS3 classification C1.
- 01HF4Q7521P5877H6PZFEWYSS3 date "2023".
- 01HF4Q7521P5877H6PZFEWYSS3 language "eng".
- 01HF4Q7521P5877H6PZFEWYSS3 type conference.
- 01HF4Q7521P5877H6PZFEWYSS3 hasPart 01HF4Q99B1NC0XED3G3BX1BAGA.pdf.
- 01HF4Q7521P5877H6PZFEWYSS3 subject "Technology and Engineering".
- 01HF4Q7521P5877H6PZFEWYSS3 doi "10.1145/3610661.3617160".
- 01HF4Q7521P5877H6PZFEWYSS3 isbn "9798400703218".
- 01HF4Q7521P5877H6PZFEWYSS3 presentedAt urn:uuid:53813b7e-0307-4f65-bcb3-697847344184.
- 01HF4Q7521P5877H6PZFEWYSS3 abstract "This paper asks if recent models for generating co-speech gesticulation also may learn to exhibit listening behaviour as well. We consider two models from recent gesture-generation challenges and train them on a dataset of audio and 3D motion capture from dyadic conversations. One model is driven by information from both sides of the conversation, whereas the other only uses the character’s own speech. Several user studies are performed to assess the motion generated when the character is speaking actively, versus when the character is the listener in the conversation. We find that participants are reliably able to discern motion associated with listening, whether from motion capture or generated by the models. Both models are thus able to produce distinctive listening behaviour, even though only one model is truly a listener, in the sense that it has access to information from the other party in the conversation. Additional experiments on both natural and model-generated motion finds motion associated with listening to be rated as less human-like than motion associated with active speaking.".
- 01HF4Q7521P5877H6PZFEWYSS3 author 034899FA-C938-11E5-A139-C70DB5D1D7B1.
- 01HF4Q7521P5877H6PZFEWYSS3 author 8A3BD710-C110-11E8-A453-F6F55607D3EF.
- 01HF4Q7521P5877H6PZFEWYSS3 author urn:uuid:3ae204e4-d7e9-497c-8aa7-1399a14d5f2b.
- 01HF4Q7521P5877H6PZFEWYSS3 dateCreated "2023-11-13T16:11:16Z".
- 01HF4Q7521P5877H6PZFEWYSS3 dateModified "2024-10-29T17:36:28Z".
- 01HF4Q7521P5877H6PZFEWYSS3 name "'Am I listening?' : evaluating the quality of generated data-driven listening motion".
- 01HF4Q7521P5877H6PZFEWYSS3 pagination urn:uuid:c5c2ac8d-6ffc-4540-9f46-626b9e21cd4b.
- 01HF4Q7521P5877H6PZFEWYSS3 publisher urn:uuid:f0962165-1701-4247-9a73-2a1a3f61f4d7.
- 01HF4Q7521P5877H6PZFEWYSS3 sameAs LU-01HF4Q7521P5877H6PZFEWYSS3.
- 01HF4Q7521P5877H6PZFEWYSS3 sourceOrganization urn:uuid:0b3926ab-a423-4ba8-935e-ff8513c7a6a3.
- 01HF4Q7521P5877H6PZFEWYSS3 type C1.