Future Directions in Spoken Dialog Systems: A Community of Possibilities

摘要

A spoken dialog system consists of a number of non-trivially interacting components. In order to allow new students, researchers and developers to meaningfully and relatively rapidly enter the field it is critical that, despite their complexity, the resources be accessible and easy to use. Everyone should be able to start building new technologies without spending a significant amount of time re-inventing the wheel. There are four levels of support that we believe new entrants should have. 1) A flexible open source system that runs on many different operating systems, is well documented and supports both simple and complex dialog systems. 2) Logs and speech files from a large number of dialogs that enable analysis and training of new systems and techniques. 3) An actual set of real users that speak to the system on a regular basis. 4) The ability to run studies on complete real user platforms.