Dialog in the Open World: Platform and Applications
D. Bohus, and E. Horvitz. Proceedings of the 11th International Conference on Multimodal Interfaces and the 6th Workshop on Machine Learning for Multimodal Interfaces (ICMI-MLMI '09), Cambridge, MA, USA, page 31-38. (2009)
DOI: 10.1145/1647314.1647323
Abstract
We review key challenges of developing spoken dialog systems that can engage in interactions with one or multiple participants in relatively unconstrained environments. We outline a set of core competencies for open-world dialog, and describe three prototype systems. The systems are built on a common underlying conversational framework which integrates an array of predictive models and component technologies, including speech recognition, head and pose tracking, probabilistic models for scene analysis, multiparty engagement and turn taking, and inferences about user goals and activities. We discuss the current models and showcase their function by means of a sample recorded interaction, and we review results from an observational study of open-world, multiparty dialog in the wild.
Proceedings of the 11th International Conference on Multimodal Interfaces and the 6th Workshop on Machine Learning for Multimodal Interfaces (ICMI-MLMI '09), Cambridge, MA, USA
year
2009
pages
31-38
file
ACM Digital Library:2009/BohusHorvitz09ICMI.pdf:PDF
%0 Conference Paper
%1 BohusHorvitz09ICMI
%A Bohus, Dan
%A Horvitz, Eric
%B Proceedings of the 11th International Conference on Multimodal Interfaces and the 6th Workshop on Machine Learning for Multimodal Interfaces (ICMI-MLMI '09), Cambridge, MA, USA
%D 2009
%K v1205 acm paper ai interface multimodal dialog user team interaction zzz.th.c4
%P 31-38
%R 10.1145/1647314.1647323
%T Dialog in the Open World: Platform and Applications
%X We review key challenges of developing spoken dialog systems that can engage in interactions with one or multiple participants in relatively unconstrained environments. We outline a set of core competencies for open-world dialog, and describe three prototype systems. The systems are built on a common underlying conversational framework which integrates an array of predictive models and component technologies, including speech recognition, head and pose tracking, probabilistic models for scene analysis, multiparty engagement and turn taking, and inferences about user goals and activities. We discuss the current models and showcase their function by means of a sample recorded interaction, and we review results from an observational study of open-world, multiparty dialog in the wild.
@inproceedings{BohusHorvitz09ICMI,
abstract = {We review key challenges of developing spoken dialog systems that can engage in interactions with one or multiple participants in relatively unconstrained environments. We outline a set of core competencies for open-world dialog, and describe three prototype systems. The systems are built on a common underlying conversational framework which integrates an array of predictive models and component technologies, including speech recognition, head and pose tracking, probabilistic models for scene analysis, multiparty engagement and turn taking, and inferences about user goals and activities. We discuss the current models and showcase their function by means of a sample recorded interaction, and we review results from an observational study of open-world, multiparty dialog in the wild.},
added-at = {2012-05-30T10:43:18.000+0200},
author = {Bohus, Dan and Horvitz, Eric},
biburl = {https://www.bibsonomy.org/bibtex/2710ede4c3473b0f1998c6b6e7e56f038/flint63},
booktitle = {Proceedings of the 11th International Conference on Multimodal Interfaces and the 6th Workshop on Machine Learning for Multimodal Interfaces (ICMI-MLMI '09), Cambridge, MA, USA},
doi = {10.1145/1647314.1647323},
file = {ACM Digital Library:2009/BohusHorvitz09ICMI.pdf:PDF},
groups = {public},
interhash = {97a0cdf41cafac3f64a20cc46416ac85},
intrahash = {710ede4c3473b0f1998c6b6e7e56f038},
keywords = {v1205 acm paper ai interface multimodal dialog user team interaction zzz.th.c4},
pages = {31-38},
timestamp = {2018-04-16T12:34:07.000+0200},
title = {Dialog in the Open World: Platform and Applications},
username = {flint63},
year = 2009
}