Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
The Back Seat Driver is a research prototype of a system to use speech synthesis as a naviga-tional aid for an automobile equipped with localiza-tion equipment. We are evaluating the user interface by field trials. As this is work in progress, this paper will primarily give an overview of the system and describe its components. Included will be discussion of the map database, route finding algorithm, repair strategies, and the discourse generator. With advances in navigation technology and automotive electronics[3,8] has come increasing interest in cars that know where they are and can help you figure out how to reach your destination. Most prototype projects have used various forms of display to present this information , and not all of them have included route finding ability~2,5,7,10,12,13,14,15,18,20,21] For safety reasons, a display may not be particularly suited to this task, moreover there is some evidence that drivers do better following spoken directions than reading maps [19]. Our project, the Back Seat Driver, uses synthetic speech to give driving directions in real time. It plans a route, talks the driver through the route, and not only warns the driver when she has made an error, but also plans an alternate, corrective route. This paper is an overview describing work in progress. We hope to publish more detailed explanations of the various portions a t a later date. At the time of this writing (June, 1989) we have a working system on the road and are simultaneously conducting field trials and improving the direction giving ability and database. Although we do not aspire to prove that voice is better than graphics for direction giving, we do aim to build an optimal system. Early results are very encouraging, suggesting that speech may prove to be a powerful technology in automobiles of the future. Talking about Directions There are many factors which contribute to good route description by people, some of which our system only touches on. The problem is complex and simple solutions are not likely to produce comfortable interfaces.
The Back Seat Driver is a research prototype of a system to use speech synthesis as a naviga-tional aid for an automobile equipped with localiza-tion equipment. We are evaluating the user interface by field trials. As this is work in progress, this paper will primarily give an overview of the system and describe its components. Included will be discussion of the map database, route finding algorithm, repair strategies, and the discourse generator. With advances in navigation technology and automotive electronics[3,8] has come increasing interest in cars that know where they are and can help you figure out how to reach your destination. Most prototype projects have used various forms of display to present this information , and not all of them have included route finding ability~2,5,7,10,12,13,14,15,18,20,21] For safety reasons, a display may not be particularly suited to this task, moreover there is some evidence that drivers do better following spoken directions than reading maps [19]. Our project, the Back Seat Driver, uses synthetic speech to give driving directions in real time. It plans a route, talks the driver through the route, and not only warns the driver when she has made an error, but also plans an alternate, corrective route. This paper is an overview describing work in progress. We hope to publish more detailed explanations of the various portions a t a later date. At the time of this writing (June, 1989) we have a working system on the road and are simultaneously conducting field trials and improving the direction giving ability and database. Although we do not aspire to prove that voice is better than graphics for direction giving, we do aim to build an optimal system. Early results are very encouraging, suggesting that speech may prove to be a powerful technology in automobiles of the future. Talking about Directions There are many factors which contribute to good route description by people, some of which our system only touches on. The problem is complex and simple solutions are not likely to produce comfortable interfaces.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.