Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Channel model (1)
- Continuous speech recognizer (1)
- Control problems (1)
- Data compression (1)
- Database (1)
-
- Distance function (1)
- Evolutionary computation (1)
- Formal methods (1)
- Hardware design (1)
- Mathematical logic systems (1)
- Neural networks (1)
- Post-correction (1)
- Post-processing (1)
- Procedural rationality (1)
- Radial basis function networks (1)
- Rational decision-making (1)
- Recognition errors (1)
- Semi-structured text (1)
- Speech interpretation (1)
- Speech recognition (1)
- Speech recognizer (1)
- Spoken dialogue systems (1)
- Training sets (1)
- Word accuracy (1)
Articles 1 - 8 of 8
Full-Text Articles in Physical Sciences and Mathematics
Procedurally Rational Decision-Making And Control, Richard L. Frost, Michael A. Goodrich, Wynn C. Stirling
Procedurally Rational Decision-Making And Control, Richard L. Frost, Michael A. Goodrich, Wynn C. Stirling
Faculty Publications
Substantive rationality requires a decision-maker to be a utility maximizer; under this paradigm, the decision is paramount, and not dependent on the computational process used to obtain it. Procedural rationality is dependent on the method used to make the decision; reasonableness of the procedure is paramount. Well-formed problems are amenable to substantive rationality; ill-formed problems are not, but are amenable to procedural rationality. To qualify as being procedurally rational, a methodology must possess a sound epistemological basis, it must be amenable to a formal design synthesis procedure, and it must be consistent with substantive rationality. Epistemic utility theory forms the …
A Fertility Channel Model For Post-Correction Of Continuous Speech Recognition, Eric K. Ringger, James F. Allen
A Fertility Channel Model For Post-Correction Of Continuous Speech Recognition, Eric K. Ringger, James F. Allen
Faculty Publications
We have implemented a post-processor called SPEECHPP to correct word-level errors committed by an arbitrary speech recognizer. Applying a noisy-channel model, SPEECHPP uses a Viterbi beam-search that employs language and channel models. Previous work demonstrated that a simple word-for-word channel model was sufficient to yield substantial incieases in word accuracy. This paper demonstrates that some improvements in word accuracy result from augmenting the channel model with an account of word fertility in the channel. This work further demonstrates that a modern continuous speech recognizer can be used in "black-box" fashion for robustly recognizing speech for which the recognizer was not …
Robust Optimization Using Training Set Evolution, Tony R. Martinez, Dan A. Ventura
Robust Optimization Using Training Set Evolution, Tony R. Martinez, Dan A. Ventura
Faculty Publications
Training Set Evolution is an eclectic optimization technique that combines evolutionary computation (EC) with neural networks (NN). The synthesis of EC with NN provides both initial unsupervised random exploration of the solution space as well as supervised generalization on those initial solutions. An assimilation of a large amount of data obtained over many simulations provides encouraging empirical evidence for the robustness of Evolutionary Training Sets as an optimization technique for feedback and control problems.
A Robust System For Natural Spoken Dialogue, Eric K. Ringger, James F. Allen, Bradford W. Miller, Teresa Sikorski
A Robust System For Natural Spoken Dialogue, Eric K. Ringger, James F. Allen, Bradford W. Miller, Teresa Sikorski
Faculty Publications
This paper describes a system that leads us to believe in the feasibility of constructing natural spoken dialogue systems in task-oriented domains. It specifically addresses the issue of robust interpretation of speech in the presence of recognition errors. Robustness is achieved by a combination of statistical error post-correction, syntactically- and semantically-driven robust parsing, and extensive use of the dialogue context. We present an evaluation of the system using time-to-completion and the quality of the final solution that suggests that most native speakers of English can use the system successfully with virtually no training.
Heterogeneous Radial Basis Function Networks, Tony R. Martinez, D. Randall Wilson
Heterogeneous Radial Basis Function Networks, Tony R. Martinez, D. Randall Wilson
Faculty Publications
Radial Basis Function (RBF) networks typically use a distance function designed for numeric attributes, such as Euclidean or city-block distance. This paper presents a heterogeneous distance function which is appropriate for applications with symbolic attributes, numeric attributes, or both. Empirical results on 30 data sets indicate that the heterogeneous distance metric yields significantly improved generalization accuracy over Euclidean distance in most cases involving symbolic attributes.
A Brief Introduction To Formal Methods, Paul E. Black, Kelly M. Hall, Michael D. Jones, Trent N. Larson, Phillip J. Windley
A Brief Introduction To Formal Methods, Paul E. Black, Kelly M. Hall, Michael D. Jones, Trent N. Larson, Phillip J. Windley
Faculty Publications
As hardware designs grow in size and complexity, current design methods are proving less adequate. Current methods for specification, design, and test are typically empirical or informal, that is, they are based on experience and argument. Formal methods are solidly based on mathematical logic systems and precise rules of inference. Formal methods offer a discipline which complements current methods so designers can successfully meet the demand for high performance systems. Formal methods covers a broad and diverse set of techniques aimed at improving computer correctness. This paper explains the role of specifications and implementation models in formal methods, and different …
Error Correction Via A Post-Processor For Continuous Speech Recognition, Eric K. Ringger, James F. Allen
Error Correction Via A Post-Processor For Continuous Speech Recognition, Eric K. Ringger, James F. Allen
Faculty Publications
This paper presents a new technique for overcoming several types of speech recognition errors by post-processing the output of a continuous speech recognizer. The post-processor output contains fewer errors, thereby making interpretation by higher-level modules, such as a parser, in a speech understanding system more reliable. The primary advantage to the post-processing approach over existing approaches for overcoming SR errors lies in its abilityto introduce options that are not available in the SR module’s output. This work provides evidence for the claim that a modern continuous speech recognizer can be used successfully in “black-box” fashion for robustly interpreting spontaneous utterances …
Compressing Semi-Structured Text Using Hierarchical Phrase Identifications, Dan R. Olsen Jr., Craig G. Nevill-Manning, Ian H. Witten
Compressing Semi-Structured Text Using Hierarchical Phrase Identifications, Dan R. Olsen Jr., Craig G. Nevill-Manning, Ian H. Witten
Faculty Publications
The structure of this paper is as follows. We begin by identifying some characteristics of semi-structured text that have special relevance to data compression. We then give a brief account of a particular large textual database, and describe a compression scheme that exploits its structure. In addition to providing compression, the system gives some insight into the structure of the database. Finally we show how the hierarchical grammar can be generalized, first manually and then automatically, to yield further improvements in compression performance.