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

TL;DR

DialPort is a new platform that links academic spoken dialog systems with real users and external resources, enabling practical testing and development of dialog technologies.

Contribution

It introduces a distributed, multi-modal dialog framework that facilitates easy integration of diverse systems and external APIs for real-world spoken dialog research.

Findings

Connected multiple academic dialog systems to real users

Integrated external resources like weather and Yelp APIs

Demonstrated successful multi-domain dialog interactions

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.