Perceptrons
Speech Recognition Experiments with Perceptrons
This paper looks at two more difficult vocabularies, the alphabetic E-set and a set of polysyllabic words. The E-set is difficult because it contains weak discriminants and polysyllables are difficult because of timing variation. Polysyllabic word recognition is aided by a time pre-alignment technique based on dynamic programming andE-set recognition is improved by focusing attention. Recognition accuracies are better than 98% for both vocabularies when implemented with a single layer perceptron. INTRODUCTION Artificial neural networks perform well on simple pattern recognition tasks.
Speech Recognition Experiments with Perceptrons
ABSTRACT Artificial neural networks (ANNs) are capable of accurate recognition of simple speech vocabularies such as isolated digits [1]. This paper looks at two more difficult vocabularies, the alphabetic E-set and a set of polysyllabic words. The E-set is difficult because it contains weak discriminants and polysyllables are difficult because of timing variation. Polysyllabic word recognition is aided by a time pre-alignment technique based on dynamic programming and E-set recognition is improved by focusing attention. Recognition accuracies are better than 98% for both vocabularies when implemented with a single layer perceptron.
Analysis of a four-layer series-coupled perceptron
Block, H. D. | Knight, B. | Rosenblatt, F.
Rev. Modern Physics, 34 (1), 275-82
On the convergence of reinforcement procedures in simple perceptrons
Report VG-1196-G-4, Cornell Aeronautical Laboratory.
The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain
Psychological Review, Vol. 65, pp. 386 ff.
The Perceptron: A Theory of Statistical Separability in Cognitive Systems
Report VG-1196-G-1, Cornell Aeronautical Laboratory, Buffalo, NY