IPUS: an architecture for the integrated processing and understanding of signals

Lesser, Victor; Nawab, S. Hamid; Klassner, Frank

doi:10.1016/0004-3702(94)00033-w

Cited by 41 publications

(17 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This basic paradigm of monitoring, detection, analysis and adaptation is similar to the approach laid out but never implemented for use in organizational self-design (Corkill & Lesser, 1983); this basic paradigm was later partially implemented as an approach to metalevel control for a single-agent interpretation system (Hudlická & Lesser, 1984, and more recently completely implemented in (Lesser, Nawab, & Klassner, 1995).…”

mentioning

confidence: 99%

Untitled

Sugawara

Lesser

1998

Machine Learning

View full text Add to dashboard Cite

Abstract.Coordination is an essential technique in cooperative, distributed multiagent systems. However, sophisticated coordination strategies are not always cost-effective in all problem-solving situations. This paper presents a learning method to identify what information will improve coordination in specific problem-solving situations. Learning is accomplished by recording and analyzing traces of inferences after problem solving. The analysis identifies situations where inappropriate coordination strategies caused redundant activities, or the lack of timely execution of important activities, thus degrading system performance. To remedy this problem, situation-specific control rules are created which acquire additional nonlocal information about activities in the agent networks and then select another plan or another scheduling strategy. Examples from a real distributed problem-solving application involving diagnosis of a local area network are described.

show abstract

mentioning

confidence: 99%

Untitled

Sugawara

Lesser

1998

Machine Learning

View full text Add to dashboard Cite

show abstract

“…Speech recognizers similarly ignore periodicity, although perceptual experiments demonstrate pitch to be an important basis for sound organization [12]. Few CASA systems have exploited much structure in their signals beyond local data features; top-down components rely on stored templates [5].…”

Section: Discussion Comparison To Other Approachesmentioning

confidence: 99%

“…A current theme in CASA work is iterative explanation, in which an account of a scene is constructed by attending to the successive residuals left after explaining more prominent pieces [5,3,6]. The approach adopted in this paper is to analyze mixtures of speech and environmental sounds by hypothesizing the presence of objects of both types, then iteratively refining each component.…”

Section: Introductionmentioning

confidence: 99%

Computational auditory scene analysis exploiting speech-recognition knowledge

Ellis

Proceedings of 1997 Workshop on Applications of Signal Processing to Audio and Acoustics

View full text Add to dashboard Cite

The field of computational auditory scene analysis (CASA) strives to build computer models of the human ability to interpret sound mixtures as the combination of distinct sources. A major obstacle to this enterprise is defining and incorporating the kind of high level knowledge of real-world signal structure exploited by listeners. Speech recognition, while typically ignoring the problem of nonspeech inclusions, has been very successful at deriving powerful statistical models of speech structure from training data. In this paper, we describe a scene analysis system that includes both speech and nonspeech components, addressing the problem of working backwards from speech recognizer output to estimate the speech component of a mixture. Ultimately, such hybrid approaches will require more radical adaptation of current speech recognition approaches.

show abstract

“…Specifically, we are using the IPUS framework for Integrated Processing and Understanding of Signals. As stated in [2], the IPUS paradigm is intended for "complex environments, which are characterized by variable signal-to-noise ratios Supponed by: NlCHD Biomed. Ra.…”

Section: It Frameworkmentioning

confidence: 99%

Next-generation decomposition of multi-channel EMG signals

Nawab

Wotiz

Hochstein

et al.

Proceedings of the Second Joint 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society] [Engi

View full text Add to dashboard Cite

We have developed a knowledge-based system for the improved decomposition of multi-channel EMC signals. This system incorporates streamlined andlor modified versions of the basic algorithms in the precision decomposition technique. In addition, it employs the IPUS framework from artificial intelligence to implement signal re-processing strategies for the detection and subsequent correction of decomposition erron arising from its initial signal processing stage. Experiments on real EMG data indicate that our new system has significant speed as well as accuracy advantages over previous generations of precision decomposition programs.

show abstract

IPUS: an architecture for the integrated processing and understanding of signals

Cited by 41 publications

References 14 publications

Untitled

Untitled

Computational auditory scene analysis exploiting speech-recognition knowledge

Next-generation decomposition of multi-channel EMG signals

Contact Info

Product

Resources

About