General References
Bankruptcy Prediction
Bond Rating
Chemical Engineering
Communications
Financial Forecasting
Industrial Applications
Marketing/Scheduling
Medical Diagnosis
OCR
Robotics
Speech Recognition
Application Summaries
Neural Net Reference
Company History
Customer Quotes
Customer Forum
Mailing List
Reviews
Search
FAQ
|
Books
Core Research
Papers
Feature Selection for
Improved Classification
Authors: Shaudys, Fred E.; Leen, Todd K.
Source: Proceedings of the International Joint
Conference on Neural Networks, IEEE, Baltimore, 1992
Abstract: We apply the
feature-selection technique of Fukunaga and Koontz, an
extension of the Karhunen-Loeve transformation, to spoken
letter recognition. Feedforward networks trained for
letter-pair discrimination with the new features show up
to 37% reduction in classifier error rate relative to
networks trained with spectral coefficients. This
performance increase is accompanied by a 91% reduction in
feature dimension. For three-letter discrimination, the
new features perform comparably to spectral coefficients,
with a 9\% reduction in feature dimension.
How Connectionist Models
Could Improve Markov Models for Speech Recognition
Author: Bourlard, H.A.
Source: Advanced Neural Computers (R. Eckmiller,
ed.), pp.247-254, Amsterdam: North-Holland, 1990
Continuous Speech
Recognition Using Multilayer Perceptrons With Hidden
Markov Models
Authors: Morgan, N.; Bourlard, H.
Source: International Conference on Acoustics,
Speech, and Signal Processing, pp.413-416, Alburquerque,
NM, 1990
Phoneme Recognition Using
Time-Delay Neural Networks
Authors: Waibel, A.; Hanazawa, T.; Hinton, G.;
Shikano, K.; Lang, K.J.
Source: IEEE Transactions on Acoustic, Speech,
and Signal Processing ASSP-37, 328-339, 1989
Improving Statistical Speech
Recognition
Authors: Renals, S.; Morgan, N.; Cohen, M.;
Franco, H.; Boulard, H.
Source: International Joint Conference on Neural
Networks, Vol. 2, pp. 302-307, Baltimore, MD, 1992
Radial Basis Function
Network for Speech Pattern Classification
Author: Renals, S.
Source: Electronic Letters 25, 437-439, 1989
A Recurrent Error
Propogation Speech Recognition System
Authors: Robinson, A.J.; Fallside, F.
Source: Computer Speech and Language 5, 259-274,
1991
Review of Neural Networks
for Speech Recognition
Author: Lippmann, R.P.
Source: Neural Computation 1, 1-38, 1989
Active Research
Sites
Recent Publications of the Realization Group at
ICSI
Interactive Systems Labs-SPEECH PUBLICATIONS
ISIS Publications Overview
OGI
Center for Spoken Language Understanding
CAS-CNS On-Line Publications
SVR Group
|
