Speech is the most natural modality for humans use to communicate with other people, agents and complex systems. A spoken dialogue system must be robust to noise and able to mimic human conversational behavior, like correcting misunderstandings, answering simple questions about the task and understanding most well formed inquiries or commands. The system aims to understand the meaning of the human utterance, and if it does not, then it discards the utterance as being meant for someone else. The first operational system is Clarissa, a conversational procedure reader and navigator, which will be used in a System Development Test Objective (SDTO) on the International Space Station (ISS) during Expedition 10. In the present environment one astronaut reads the procedure on a Manual Procedure Viewer (MPV) or paper, and has to stop to read or turn pages, shifting focus from the task. Clarissa is designed to read and navigate ISS procedures entirely with speech, while the astronaut has his eyes and hands engaged in performing the task. The system also provides an MPV like graphical interface so the procedure can be read visually. A demo of the system will be given.
Clarissa Spoken Dialogue System for Procedure Reading and Navigation
2004-01-01
Preprint
No indication
English
Navigation-Orientated Natural Spoken Language Understanding for Intelligent Vehicle Dialogue
British Library Conference Proceedings | 2017
|Spoken Dialogue Technologies for Drivers
British Library Conference Proceedings | 2002
|Spoken dialogue technologies for drivers
Automotive engineering | 2002
|A Generic Framework for Spoken Dialogue System and Its Application to a Car Navigation Task
British Library Conference Proceedings | 1999
|