Publications
-
Connectionist Gender Adaptation in a Hybrid Neural Network / Hidden Markov Model Speech Recognition System
An approach to modeling long-term consistencies in peech signal within the framework of a hybrid Hidden Markov Model (HMM) / Multilayer Perceptron (MLP peaker-independent continuous-speech recognition system is presented.
-
The Design Space of Frame Knowledge Representation Systems
This paper surveys the FRS design space in search of design principles for FRSs.
-
Characterizing diagnoses and systems
In this paper we analyze the concept of diagnosis in depth exploiting the notions of implicate/implicant and prime implicate/implicant.
-
Fundamentals Of Deductive Program Synthesis
An informal tutorial is presented for program synthesis, with an emphasis on deductive methods. According to this approach, to construct a program meeting a given specification, we prove the existence…
-
Integrating Multiple Knowledge Sources for Detection and Correction of Repairs in Human-computer Dialog
We present here criteria and techniques for automatically detecting the presence of a repair, its location, and making the appropriate correction. The criteria involve integration of knowledge from several sources:…
-
Narrow views, old talks, new beginnings
A response to "Prolegomena to Any Future Qualitative Physics," which attempts to clarify the goals of the field and describe some of the major research efforts.
-
Detection and Correction Of Repairs In Human-Computer Dialog
We present here criteria and techniques for automatically detecting the presence of a repair, its location, and making the appropriate correction. The criteria involve integration of knowledge from several sources:…
-
Lucid and Intensional Logic
-
The Representation Space Paradigm Of Concurrent Evolving Object Descriptions
This paradigm is designed to be used by the perception system of an autonomous robot that needs to describe many types of objects, initially detects objects at a distance and…
-
Automatic Detection and Correction of Repairs in Human-computer Dialog
We present here criteria and techniques for automatically detecting the presence of a repair, its location, and making the appropriate correction.
-
Multiple-State Context-Dependent Phonetic Modeling with MLPs
In this paper we present a new MLP architecture and training procedure for modeling context-dependent phonetic classes with a sequence of distributions.
-
Camera self-calibration: theory and experiments
In this paper a complete method for calibrating a camera is presented. In contrast with existing methods it does not require a calibration object with a known 3D shape.