dc.contributor.author | Mc Donnell, Rachel | en |
dc.date.accessioned | 2019-12-13T13:23:17Z | |
dc.date.available | 2019-12-13T13:23:17Z | |
dc.date.created | November 05 - 08, 20 | en |
dc.date.issued | 2018 | en |
dc.date.submitted | 2018 | en |
dc.identifier.citation | Ylva Ferstl, Rachel McDonnell, Investigating the use of recurrent motion modelling for speech gesture generation, 18th International Conference on Intelligent Virtual Agents, Sydney, NSW, Australia, November 05 - 08, 20, 2018, 93-98 | en |
dc.identifier.other | Y | en |
dc.description | PUBLISHED | en |
dc.description | Sydney, NSW, Australia | en |
dc.description.abstract | The growing use of virtual humans demands generating increasingly realistic behavior for them while minimizing cost and time. Gestures are a key ingredient for realistic and engaging virtual agents and consequently automatized gesture generation has been a popular area of research. So far, good gesture generation has relied on explicit formulation of if-then rules and probabilistic modelling of annotated features. Machine learning approaches have yielded only marginal success, indicating a high complexity of the speech-to-motion learning task. In this work, we explore the use of transfer learning using previous motion modelling research to improve learning outcomes for gesture generation from speech. We use a recurrent network with an encoder-decoder structure that takes in prosodic speech features and generates a short sequence of gesture motion. We pre-train the network with a motion modelling task. We recorded a large multimodal database of conversational speech for the purpose of this work. | en |
dc.format.extent | 93-98 | en |
dc.language.iso | en | en |
dc.rights | Y | en |
dc.subject | Machine learning | en |
dc.subject | Character animation | en |
dc.subject | Motion synthesis | en |
dc.subject | Behaviour generation | en |
dc.subject | Recurrent networks | en |
dc.subject | Deep learning | en |
dc.title | Investigating the use of recurrent motion modelling for speech gesture generation | en |
dc.title.alternative | 18th International Conference on Intelligent Virtual Agents | en |
dc.type | Conference Paper | en |
dc.type.supercollection | scholarly_publications | en |
dc.type.supercollection | refereed_publications | en |
dc.identifier.peoplefinderurl | http://people.tcd.ie/ramcdonn | en |
dc.identifier.rssinternalid | 194193 | en |
dc.identifier.doi | http://dx.doi.org/10.1145/3267851.3267898 | en |
dc.rights.ecaccessrights | openAccess | |
dc.subject.TCDTheme | Creative Technologies | en |
dc.subject.TCDTag | Computer Graphics | en |
dc.subject.TCDTag | Computer Graphics | en |
dc.identifier.rssuri | https://dl.acm.org/citation.cfm?doid=3267851.3267898 | en |
dc.identifier.orcid_id | 0000-0002-1957-2506 | en |
dc.contributor.sponsor | Science Foundation Ireland (SFI) | en |
dc.contributor.sponsorGrantNumber | 13/RC/2016 | en |
dc.contributor.sponsor | Science Foundation Ireland (SFI) | en |
dc.identifier.uri | https://dl.acm.org/citation.cfm?doid=3267851.3267898 | |
dc.identifier.uri | http://hdl.handle.net/2262/91094 | |