English

DialPort: Connecting the Spoken Dialog Research Community to Real User Data

Artificial Intelligence 2016-06-13 v1 Computation and Language

Abstract

This paper describes a new spoken dialog portal that connects systems produced by the spoken dialog academic research community and gives them access to real users. We introduce a distributed, multi-modal, multi-agent prototype dialog framework that affords easy integration with various remote resources, ranging from end-to-end dialog systems to external knowledge APIs. To date, the DialPort portal has successfully connected to the multi-domain spoken dialog system at Cambridge University, the NOAA (National Oceanic and Atmospheric Administration) weather API and the Yelp API.

Keywords

Cite

@article{arxiv.1606.02562,
  title  = {DialPort: Connecting the Spoken Dialog Research Community to Real User Data},
  author = {Tiancheng Zhao and Kyusong Lee and Maxine Eskenazi},
  journal= {arXiv preprint arXiv:1606.02562},
  year   = {2016}
}

Comments

Under Peer Review of SigDial 2016