Multi-party, Multi-issue, Multi-strategy Negotiation for Multi-modal Virtual Agents
IVA '08 Proceedings of the 8th international conference on Intelligent Virtual Agents
Towards natural language understanding of partial speech recognition results in dialogue systems
NAACL-Short '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers
SIGDIAL '09 Proceedings of the SIGDIAL 2009 Conference: The 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Towards more comprehensive listening behavior: beyond the bobble head
IVA'11 Proceedings of the 10th international conference on Intelligent virtual agents
Incremental speech understanding in a multi-party virtual human dialogue system
NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstration Session
Hi-index | 0.00 |
This demonstration highlights some emerging capabilities for incremental speech understanding and processing in virtual human dialogue systems. This work is part of an ongoing effort that aims to enable realistic spoken dialogue with virtual humans in multi-party negotiation scenarios (Plüss et al., 2011; Traum et al., 2008). In these negotiation scenarios, ideally the virtual humans should demonstrate fluid turn-taking, complex reasoning, and appropriate responses based on factors like trust and emotions. An important component in achieving this naturalistic behavior is for the virtual humans to begin to understand and in some cases respond in real time to users' speech, as the users are speaking (DeVault et al., 2011b). These responses could include relatively straightforward turn management behaviors, like having a virtual human recognize when it is being addressed and turn to look at the user. They could also include more complex responses such as emotional reactions to what users are saying.