The DARPA SLS Program is developing a technology that has been justified, at least in part, by its potential relevance to military applications.In an effort to demonstrate the relevance of SIS technology to real-world military applications, BBN has undertaken the task of providing a spoken language interface to DART, a system for military logistical transportation planning.We discuss the transportation planning process, describe the real-world DART system, identify parts of the system where spoken language can facilitate planning, and describe BBN's work towards porting the HARC SIS system to the DART domain. TRANSPORTATION PLANNINGLogistical transportation planning is the process of determining how to get people and cargo from where they are to where they need to be. Inter-theatre movements of personnel and supplies around the world are currently planned for the Army, Navy, Air Force, and other services by USTRANSCOM (the US TRANSportation COMmand) which operates under the Joint Chiefs of Staff. The transportation plarming process is quite complex, involving very large databases of movement requirements, and information about personnel, cargo, transportation assets, and geographic locations. Currently, the human interface to military planning systems is relatively enmbersome and unintelligent, which adds extra complexity to the planner's task.As a domain for the application of spoken language, military transportation planning has a number of advantages:1. Transportation planning is an essential military function and successful application of spoken language would be both useful to TRANSCOM and visible to other potential military users of SLS technology.2. The concept of planning movements of people and supplies can be understood by a wide audience.3. The application is non-trivial and, in the DART context that we will describe, affords opportunities for applying spoken language understanding at many levels of sophistication.4. Current efforts to improve the planning process using nonspeech technology have been weU-received, and cooperative users may be available as close as Scott Air Force Base near St. Louis.5. An unclassified development database is available in Oracle on a Son. THE DART SYSTEMBBN is currently involved in an effort to improve the transportation process using non-speech teclmology. The DART (Dynamic Analysis and Replanning Tool) project 1 , is demonstrating the operational impact of AI planning and scheduling technology on transportation planning at USTRANSCOM. DART addresses an urgent need for fast and accurate plan generation and evaluation to support both longrange, hypothetical planning and planning in such crisis-response operations as those in the Middle East.The current DART system [1] is in use at Scott Air Force Base and other locations around the globe. The workstation environment which has been installed at TRANSCOM to support DART is already being used and has been credited with reducing routine plan analysis from 3 days to I day [2].
Typically, real-time speech recognition -if achieved at all -is accomplished either by greatly simplifying the processing to be done, or by the use of special-purpose hardware. Each of these approaches has obvious problems. The former results in a substantial loss in accuracy, while the latter often results in obsolete hardware being developed at great expense and delay. Starting in 1990 [1] [2] we have taken a different approach based on modifying the algorithms to provide increased speed without loss in accuracy. Our goal has been to use commercially available off-the-shelf (COTS) hardware to perform speech recognition. Initially, this meant using workstations with powerful but standard signal processing boards acting as accelerators. However, even these signal processing boards have two significant disadvantages:1. They often cost as much as the workstation they are plugged into.. The interface between each board and workstation is complicated, and always different for each combination of workstation and board.To make speech recognition available to a broad base of users at an affordable cost, we have eliminated these disadvantages by developing algorithms that are able to operate in real-time on COTS workstations without requiring additional add-on hardware and without decreasing recognition speed and accuracy. An additional advantage is that we are able to benefit from the improvements in workstation price and performance, with very minimal porting effort. The BBN RUBY TM system, a robust commercialization of the BYBLOS TM speech recognition technology, is the result of this development effort. At the workshop, we demonstrated two example systems that employ the RUBY speech recognition system.Both demonstrations run on Silicon Graphics workstations (Personal IRIS 4D/35 and Indigo), which contain a builtin programmable A/D-D/A. The signal processing and vector quantization, which runs in a separate process from the recognition search, communicates with the recognition search via network sockets. We have reduced the computation required for this front end processing to the point where it requires little enough of the CPU so that there is enough left over to perform the more expensive search in real time.Since accuracy is our primary concern, we have verified that this signal processing results in the same accuracy as our previous signal processing software. REAL-TIME ATIS SYSTEMThe ATIS demonstration integrated BBN's DELPHI natural language understanding system with the RUBY speech recognition component. RUBY is used as a black-box, controlled entirely through an application programmers interface (API). The natural language component is our current research system, which runs as a separate process. Both processes run on the same processor, although not at the same time. The NL processing is performed strictly after the speech recognition, since competing for the same processor could not make it faster. (If two separate processors are available, the processing can be overlapped as describedThe speech recognit...
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.
customersupport@researchsolutions.com
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.