Publication - Discrepancy Directed Model Acquisition for Adaptive Perceptual Systems
| Authors: | Bhandaru, M. and Lesser, V. | ||||
| Title: | Discrepancy Directed Model Acquisition for Adaptive Perceptual Systems | ||||
| Abstract: | For complex perceptual tasks that are characterized by object occlusion and non-stationarity recognition systems with adaptive signal processing front-ends have been developed. These systems rely on hand-crafted symbolic object models which constitutes a knowledge acquisition bottleneck. We propose an approach to automate object model acquisition that relies on the detection and resolution of signal processing and interpretation discrepancies. The approach is applied to the task of acquiring acoustic-event models for the Sound Understanding Testbed (SUT). | ||||
| Keywords: | IPUS | ||||
| Publication: | Computational Auditory Scene Analysis, pp. 215 - 232 | ||||
| Publisher: | Rosenthal and Okuno (eds.) NJ: Lawrence Erlbaum Associates | ||||
| Date: | January 1998 | ||||
| Sources: |
PS: ftp://ftp.cs.umass.edu/pub/lesser/bhandaru-ijcai95ws-casa.ps PDF: /Documents/bhandaru-ijcai95ws-casa.pdf |
||||
| Reference: | Bhandaru, M. and Lesser, V.. Discrepancy Directed Model Acquisition for Adaptive Perceptual Systems. Computational Auditory Scene Analysis, Rosenthal and Okuno (eds.) NJ: Lawrence Erlbaum Associates, pp. 215-232. January 1998. | ||||
| bibtex: | @article{Bhandaru-92,
author = "M. Bhandaru and V. Lesser",
title = "{Discrepancy Directed Model Acquisition for
Adaptive Perceptual Systems}",
journal = "Computational Auditory Scene Analysis",
publisher = "Rosenthal and Okuno (eds.) NJ: Lawrence Erlbaum Associates",
pages = "215-232",
month = "January",
year = "1998",
url = "http://mas.cs.umass.edu/paper/92",
}
|
||||
