Publications
-
A Robust Technique for Matching Two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry
This paper proposes a robust approach to image matching by exploiting the only available geometric constraint, namely, the epipolar constraint.
-
A Comparative Study of Speaker Adaptation Techniques
In this paper, we study various ML-based techniques and compare experimental results on data sets with recordings from nonnative and native speakers of American English. In feature-space techniques, we hypothesize…
-
Connectionist Speaker Normalization and Adaptation
We explore supervised speaker adaptation and normalization in the MLP component of a hybrid hidden Markov model/multilayer perceptron version of SRI's DECIPHER™ speech recognition system. Our approach combines both adaptation…
-
Object-Centered Surface Reconstruction: Combining Multi-Image Stereo and Shading
We argue that an object-centered representation is most appropriate for this purpose becasue it naturally accomodates multiple sources of data, multiple images (including motion sequences of a rigid object), and…
-
Training Data Clustering for Improved Speech Recognition
We present an approach to cluster the training data for automatic speech recognition (ASR). A relative entropy based distance metric between training data clusters is defined.
-
Acoustic Properties of Disfluent Repetitions
Acoustic properties of disfluent repetitions are examined to investigate two proposed functions of repeating. Repeating may serve as a filler while hesitating; alternatively, repeating may function to bridge a gap…
-
A technology of order production: computer-aided dispatch in 9-1-1 communications
-
A State-Space Striatal Model
This chapter considers the role of the striatum in computing purposeful state changes.
-
An Efficient Probabilistic Context-Free Parsing Algorithm that Computes Prefix Probabilities
We describe an extension of Earley's parser for stochastic context-free grammars that computes quantities given a stochastic context-free grammar and an input string.
-
WebWatcher: A Learning Apprentice for the World Wide Web
We describe an information seeking assistant for the world wide web. This agent, called WebWatcher, interactively helps users locate desired information by employing learned knowledge about which hyperlinks are likely…
-
Adapting CLIM Applications for Use on the World Wide Web
We have developed a Web server tool, written in Common Lisp, that allows any existing graphical user interface application written using the Common Lisp Interface Manager (CLIM) to hook easily…
-
WebWatcher: Knowledge Navigation in the World Wide Web
We describe a learning apprentice system, called WebWatcher, which both performs the kind of indexing used by Web catalogers like Lycos, and attempts to exploit the two sources of knowledge…