Speech Recognition Experiments with Perceptrons
暂无分享,去创建一个
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.
[1] T.H. Crystal,et al. Linear prediction of speech , 1977, Proceedings of the IEEE.
[2] Terrence J. Sejnowski,et al. NETtalk: a parallel network that learns to read aloud , 1988 .
[3] L. Rabiner,et al. An algorithm for determining the endpoints of isolated utterances , 1974, The Bell System Technical Journal.
[4] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .