|
Fluent behavior realization, conversational computer animation and visual prosody| old_uid | 14653 |
|---|
| title | Fluent behavior realization, conversational computer animation and visual prosody |
|---|
| start_date | 2014/11/19 |
|---|
| schedule | 14h |
|---|
| online | no |
|---|
| location_info | 3e étage, salle DB312 |
|---|
| summary | Human conversations are highly dynamic, responsive interactions. In such interactions, utterances are produced incrementally, subject to on-the-fly adaptation and (self) interruptions. I'm interested in developing user interfaces with virtual humans that allow such a fluent interaction with a human user. My current research focuses both on the general architecture design of such user interfaces and specifically on enabling multimodal behavior generation that allows fluent interaction.
To this end we have developed AsapRealizer, a BML behavior realizer which has unique capabilities that enable an intuitive and human-like fluent interaction with embodied conversational agents: it provides a flexible behavior plan representation, adaptation and interruption of ongoing behavior (speech, gesture, facial expression), and allows the behavior to be composed out of small increments so that it can be realized with low latency. During this talk I will introduce AsapRealizer, give an overview of its capabilities for fluent behavior realization and show some applications that have profited from it. I will also discuss the behavior and intent planning possibilities enabled by AsapRealizer and show some of our recent work on this.
Related to fluent interaction, I am also interested in conversational animation techniques that allow it. In addition to being perceived as realistic, conversational animation has several requirements that set it apart from less interactive animation such as motion executed in animation movies and computer games: conversational animation requires semantic and temporal coordination with speech, is to be executed in real-time and is subject to adaptation.
During my stay in Paris I aim to combine my two research interests and work (in collaboration with Yu Ding and Catherine Pelachaud) on real-time visual prosody for virtual humans: we aim to build a model that allows the real-time synthesis of head and eyebrow motion on the basis of prosodic features of accompanying speech provided by a Text-To-Speech-system. This model is to be designed in such a way that it is possible to embed it in virtual human applications. I will discuss the preliminary design of the model and the research challenges involved. |
|---|
| responsibles | <not specified> |
|---|
| |
|