Publications
-
An Experimental Study of Acoustic Adaptation Algorithms
In this paper we focus on transformation-based maximum-likelihood (ML) adaptation.
-
Advisable Planning Systems
The Advisable Planner project seeks to make AI planning technology more accessible and easier to use through the metaphor of advice-taking. In particular, we are developing an advisable planning system…
-
Globe Year 1 Evaluation: Findings
Global learning and observations to benefit the environment (GLOBE) is an international environmental science and education program involving elementary and secondary school students in the collection of data concerning their…
-
Self-Calibration of a Stereo Rig from Unknown Camera Motions and Point Correspondences
We show theoretically and with experiments on real images, how it is possible to completely calibrate a stereo rig, that is to determine each camera’s intrinsic parameters and the relative…
-
Ropes: an alternative to strings
We claim that the traditional implementations of strings, and often the supported functionality, are not well suited to such general-purpose use.
-
Expert systems versus systems for experts
-
The role of intelligent systems in the national information infrastructure
AI techniques can play a central role in the development of a useful and usable NII by (1) enabling the construction of human-computer interface systems that are goal-oriented, cooperative, and…
-
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.
-
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.
-
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…