论文信息 - Online Evaluation of Response Obligation Estimation on the HALOGEN Multimodal Interaction Framework

Online Evaluation of Response Obligation Estimation on the HALOGEN Multimodal Interaction Framework

This report describes our ongoing attempt to evaluate the previously proposed method of response obligation estimation [1] in a realtime human-robot interaction with a fully automated conversational robot system based on HALOGEN, which is an infrastructural distributed framework for a multimodal multiparty dialogue system. HALOGEN has a two-stage information fusion strategy and it potentially has merits to implement multiparty human-robot interactions. We discuss interaction-oriented compensatory mechanisms for failures in response obligation estimation.

Mikio Nakano | Kotaro Funakoshi

[1] Koichi Shinoda,et al. Boredom Recognition Based on Users' Spontaneous Behaviors in Multiparty Human-Robot Interactions , 2017, MMM.

[2] Qianli Xu,et al. Designing engagement-aware agents for multiparty conversations , 2013, CHI.

[3] Seiichi Nakagawa,et al. Detection and recognition of correction utterance in spontaneously spoken dialog , 2003, INTERSPEECH.

[4] Rivka Levitan,et al. Detecting Retries of Voice Search Queries , 2014, ACL.

[5] Eric Horvitz,et al. Multiparty Turn Taking in Situated Dialog: Study, Lessons, and Directions , 2011, SIGDIAL Conference.

[6] Naoyuki Kanda,et al. A multi-expert model for dialogue and behavior control of conversational robots and agents , 2011, Knowl. Based Syst..

[7] Matthew Richardson,et al. Markov logic networks , 2006, Machine Learning.

[8] Chin-Hui Lee,et al. Detection of repetitions in spontaneous speech in dialogue sessions , 2008, INTERSPEECH.

[9] Mikio Nakano,et al. Estimating response obligation in multi-party human-robot dialogues , 2015, 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids).