The Hearsay-II system, developed during the DARPA-sponsored five-year speechunderstanding research program, represents both a specific solution to the speechunderstanding problem and a general framework for coordinating independent processes to achieve cooperative problem-solving behavior. As a computational problem, speech understanding reflects a large number of intrinsically interesting issues. Spoken sounds are achieved by a long chain of successive transformations, from intentions, through semantm and syntactic structurmg, to the eventually resulting audible acoustic waves. As a consequence, interpreting speech means effectively inverting these transformations to recover the speaker's intention from the sound. At each step in the interpretive process, ambiguity and uncertainty arise. The Hearsay-II problem-solving framework reconstructs an intention from hypothetmal interpretations formulated at various levels of abstraction. In additmn, it allocates hmlted processing resources fwst to the most promising incremental actions. The final configuration of the Hearsay-II system comprises problem-solving components to generate and evaluate speech hypotheses, and a focus-of-control mechanism to identify potentml actions of greatest value. Many of these specific procedures reveal novel approaches to speech problems. Most important, the system successfully integrates and coordinates all of these independent actlwhes to resolve uncertainty and control combmatorms. Several adaptations of the Hearsay-II framework have already been undertaken in other problem domains, and it is anticipated that this trend will contmue; many future systems necessarily will integrate diverse sources of knowledge to solve complex problems cooperatively. Discussed m this paper are the characteristics of the speech problem in particular, the specml kinds of problem-solving uncertainty in that domain, the structure of the Hearsay-II system developed to cope with that uncertamty, and the relationship between Hearsay-Irs structure and those of other speech-understanding systems. The paper is intended for the general computer science audience and presupposes no speech or artificial intelligence background.
IS. SECURITY CLASS, fo» thl» npott) UNCLASSIFIED 15«. OECLASSlFlCATION DOWNGRADING SCHEDULE 16. DISTRIBUTION STATEMENT fo* Ih'» R»por(J " /ooroved tor public release, üloi-iiLuticr. un^i^t: 17. DISTRIBUTION STATEMENT (ol Iht mba'.ract enterea in Block 3C, II
The Hearsay-II System has as its design goal recognition, understanding, and responding to connected speech utterances, particularly in situations where sentences cannot be guaranteed to agree with some predefined, restricted language model, as in the case of the Harpy System. Further, it attempts to view knowledge sources as different and independent which cannot always be integrated into single representation. It is based on the blackboard model [V. R. Lesser, R. D. Fennell, L. D. Erman, and D. R. Reddy, IEEE Trans. Acoust. Speech and Signal Process. ASSP-23, 11–23 (1975) with knowledge sources as a set of parallel processes which are activated asynchronously depending on data events. The system performs on the Information Retrieval task with accuracy comparable to that of the Harpy system, but runs about 2 to 20 times slower. More complete performance results will be reported. As we get closer to unrestricted vocabularies and nongrammaticality of spoken languages, it will be necessary to have systems which have the flexibility of Hearsay-II and the performance of Harpy. [Research supported by the Defense Advanced Research Projects Agency.]
Cimflex Teknowledgeputing program explicitly aimed to expand the range of applications that could exploit intelligent reasoning and knowledge processing. When the program began in 1985, there were few paradigms for building intelligent applications, and most applications had significant limitations. The principal paradigms derived from expert systems, blackboard systems, and objectoriented systems. Each of these system development approaches consisted of an underlying computational model, a method for organizing knowledge and other computational elements, a control regime for determining operation sequence, and a set of tools embodying these assumptions and supporting development. Table 1 lists these paradigms' principal components.Conceptual and implementation limitations prevented these paradigms from adequately addressing the complexity, diversity, and performance challenges of Strategic Computing program applications. Table 2 summarizes the principal requirements of these demanding applications and the related technological shortfalls. This article describes our efforts to develop improved methods for addressing the challenging and unmet requirements thatexisted in 1985. The results of those efforts 30 PARADIGMS IN THE MID-198OS COULD NOT HANDLE THE COMPLEXITY, DIVERSITY, OR PERFORMINCE CHALLENGES OF STRATEGIC COMPUTING APPLICATIONS. OUR GOAL WAS TO CREATE TECHNOLOGIES AND METHODOLOGIES FOR BUILDING COOPERATIVE, INTELLIGENT SYSTEMS WITH MODULAR, HETEROGENEOUS COMPONENTS.are embodied in a system engineering environment called ABE ("A Better Environment").',2 To some degree the ABE system solves each requirement and shortfall listed in Table 2. To do this, we developed several novel concepts for composing systems out of parts and for separating logical design aspects from physical realization concerns. We focus here on the following key concepts and implementations:federated cooperative computing applications, built atop diverse platforms; design and development frameworks for describing, implementing, and combining subsystems using specialized representations; module-oriented programming for recursively composing subsystems from cooperative, communicating components; high-dimensional modularity achieved by increased separation between functional and implementation aspects; modular knowledge-processing functions for increasing specialization, reuse, and standardization; and tools for system development as opposed to module development. Motivating problemsWhen our project began, artificial intelligence systems were mostly monolithic, isolated, and stand-alone. Their challenges were largely internal and self-motivated, concerning issues such as what was the best way to represent knowledge or which version of Lisp to employ. However, the driving applications of the Strategic 0885/9000/91/0600-0030 51.00 0 1991 IEEE
As part of the ARPA DSSA program, we are developing a methodology and integrating a suite of supporting tools to help specify, design, validate, package and deploy distributed intelligent control and management (DICAM) applications. Our domain of specialization is vehicle management systems, and our near-term focus is on advanced artillery systems. To attain higher levels of performance and functionality while reducing the time and cost required for development, we are recommending a generic control architecture suitable for use as a single intelligent agent or as multiple cooperating agents. This reference architecture combines a task-oriented domain controller with a meta-controller that schedules activities within the domain controller. The domain controller provides functions for model-based situation assessment and planning, and inter-controller communication. Typically, these functions are performed by components taken from a repository of reusable software. In tasks that are simple, deterministic or time-stressed, the modules may be complied into or replaced by conventional control algorithms. In complex, distributed, cooperative, non-deterministic or unstressed situations, these modules will usually exploit knowledge-based reasoning and deliberative control.To improve the controller development process, we are combining many of the best ideas from software engineering and knowledge engineering in a software environment. This environment includes a blackboard-like development workspace to represent both the software under development and the software development process itself. In this workspace, controllers are realized by mapping requirements into specializations of the reference architecture. The workspace also provides mechanisms for triggering applications of software tools, including knowledge-based software design assistants.We are currently in the third year of a five-year program. In conjunction with our collaborators at ARDEC, we have produced a schema for describing architectures which is being used by ARDEC's community of contractors, by an ARPA architecture specification project for the Joint Task Force ATD, and by the Stanford Knowledge Systems Laboratory. We have released the second major version of our development environment, which is being used at ARDEC and in support of this ARPA architecture specification program. This version of the development environment is focused on initial requirements, architecture, and design. It provides both CASE-like editing of architectures and textual browsing/editing of repository descriptions expressed in the schema mentioned above. In the remaining years of the program we will be expanding the suite of tools and improving the methodologies required to build intelligent, distributed, hybrid controllers capable of spanning multiple levels of organization and system hierarchy. This technology holds considerable promise for near-term value, and the associated methodology provides a candidate approach for realizing the goals of mega-programming practice in control software. In assessing this prospect, we discuss some of the remaining shortfalls in both methodology and tools that require additional research and development.
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.