Date of Award
6-2016
Document Type
Open Access
Degree Name
Bachelor of Science
Department
Computer Science
First Advisor
Nick Webb
Language
English
Abstract
Spoken dialogue systems are automatic, computer based systems that are a great way for people to receive important information. In this project, I created a spoken dialogue system that people can use to learn about the Computer Science Department at Union College. The system was built by populating an open source dialogue system using a graph based dialogue manager. I improved upon a previous working dialogue system by making the conversations sound more natural, improving the flexibility of the system and making the system more robust. To help with this process a corpus was created using about 200 different dialogues from about 20 people produced by Wizard of Oz Experiments. When the system was complete and implemented it was evaluated with 10 different participants to ensure the system is usable. The evaluation was based on the rates of task completion of people using the system, the number of turns a person has to achieve their goal and a survey given to participants. Based on the evaluation,the main issue that appears is from the speech recognition not working as well as it should. The graph based dialogue manger works well, provided the other components of the whole system works properly.
Recommended Citation
Isaac, Julia, "A Graph Based Departmental Spoken Dialogue System" (2016). Honors Theses. 161.
https://digitalworks.union.edu/theses/161
Included in
Communication Technology and New Media Commons, Graphics and Human Computer Interfaces Commons, Systems and Communications Commons