Supporting license plate queries for first responders using the voiceLETS system

Abstract

The need for delivering quick and accurate information to first responders, such as law enforcement officers, is important for providing them with the resources needed to do their jobs safely and effectively. The common method of information exchange from officers to emergency dispatchers is problematic in that response time and communicative consistency can result in inaccurate or untimely information. Although information requests by officers currently require the use of defined alpha codes to ensure the accuracy of vehicle license plate sequences, the proper use is inconsistent. We introduce in this paper an adaption of VoiceLETS, [1] which provides an algorithm to detect and predict license sequences without the use of alpha codes. Preliminary testing of this algorithm showed a 34.2% increase in the accuracy of tag query results. There was also a correction accuracy of 95.35% when the system attempted to correct misinterpreted characters within a query. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. ACMSE '10, April 15--17, 2010, Oxford, MS, USA