A scaly artificial neural network for speaker independent isolated word recognition using non-linear time alignment

Author

Creaney, M.J. ; Gorgui-Naguib, R.N.

Author_Institution

Dept. of Electr. & Electron. Eng., Newcastle upon Tyne Univ., UK

Volume

7

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

4431

Abstract

The use of neural networks for the recognition of isolated letters from the English alphabet is investigated. A scaly architecture neural network model is used and is trained using the error backpropagation algorithm. The architecture is varied by changing the number of inputs to the network, the number of hidden units in the network and the performance of each of these networks is compared. The nonlinear time alignment algorithm called trace segmentation is used. The use of different transfer functions within the processing units of the neural network is looked at and several versions of the sigmoid function compared

Keywords

backpropagation; neural net architecture; neural nets; speech recognition; transfer functions; English alphabet; error backpropagation; hidden units; isolated word recognition; model; nonlinear time alignment; scaly artificial neural network; sigmoid function; speaker independent speech recognition; trace segmentation; transfer functions; Artificial neural networks; Data preprocessing; Feedforward neural networks; Feedforward systems; Multi-layer neural network; Neural networks; Neurons; Pattern recognition; Speech recognition; Transfer functions;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374983

Filename

374983