AsapRealizer 2.0: The Next Steps in Fluent Behavior Realization for ECAs
نویسندگان
چکیده
Natural human interaction is highly dynamic and responsive: interlocutors produce utterances incrementally, smoothly switch speaking turns with virtually no delay, make use of on-the-fly adaptation and (self) interruptions, execute movement in tight synchrony, etc. We present the conglomeration of our research efforts in enabling the realization of such fluent interactions for Embodied Conversational Agents in the behavior realizer ‘AsapRealizer 2.0’ and show how it provides fluent realization capabilities that go beyond the state-of-the-art.
منابع مشابه
An Incremental Multimodal Realizer for Behavior Co-Articulation and Coordination
Human conversations are highly dynamic, responsive interactions. To enter into flexible interactions with humans, a conversational agent must be capable of fluent incremental behavior generation. New utterance content must be integrated seamlessly with ongoing behavior, requiring dynamic application of co-articulation. The timing and shape of the agent’s behavior must be adapted on-the-fly to t...
متن کاملTowards a Common Framework for Multimodal Generation: The Behavior Markup Language
This paper describes an international effort to unify a multimodal behavior generation framework for Embodied Conversational Agents (ECAs). We propose a three stage model we call SAIBA where the stages represent intent planning, behavior planning and behavior realization. A Function Markup Language (FML), describing intent without referring to physical behavior, mediates between the first two s...
متن کاملAsapRealizer in practice - A modular and extensible architecture for a BML Realizer
Building a complete virtual human application from scratch is a daunting task, and it makes sense to rely on existing platforms for behavior generation. When one does this, one needs to be able to adapt and extend the capabilities of the virtual human as offered by the platform, without having to make invasive modifications to the platform itself. This is not trivial to support, and not all exi...
متن کاملNext Steps for Elevating Health on Trade and Investment Policy Agendas; Comment on “How Neoliberalism Is Shaping the Supply of Unhealthy Commodities and What This Means for NCD Prevention”
Despite intergovernmental calls for greater policy coherence to tackle rising non-communicable diseases (NCDs), there has been a striking lack of coherence internationally and nationally between trade and health sectors. In this commentary, I explore the arguments by Lenucha and Thow in relation to barriers for greater coherence for NCDs, apply them to regional trade ag...
متن کاملAmalgam: A machine-learned generation module
Amalgam is a novel system for sentence realization during natural language generation. Amalgam takes as input a logical form graph, which it transforms through a series of modules involving machine-learned and knowledge-engineered sub-modules into a syntactic representation from which an output sentence is read. Amalgam constrains the search for a fluent sentence realization by following a ling...
متن کامل