Author: SRI International
-
A Phone-Dependent Confidence Measure for Utterance Rejection
An acoustic confidence measure for acceptance/rejection of recognition hypotheses for continuous speech utterances is proposed. This measure is useful for rejecting utterances that are out of domain, or contain out-of-vocabulary words or speech disfluencies.
-
Mentors In The Classroom: Bringing The World Outside In
-
Connecting The Connectivity And The Component Revolutions To Deep Curriculum Reform
-
Programming Games For Learning About Magnetism And Electricity
-
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 customizable; allow users to communicate in natural ways in a variety of modalities; and provide a consistent interface to the full range of NII services;…
-
Twin research
Twin Research Registry creates new opportunities for health and behavior research.
-
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.
-
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 self-occlusions.
-
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 an underlying transformation in the feature-space that results in a transformation of the HMM parameters.