Neural learning for articulatory speech synthesis under different statistical characteristics of acoustic input patterns

Computers and Electrical Engineering

Volumn 29, Issue 6, 2003, Pages 687-702

  Altun, H ^a   Curtis, K M ^b   Yalcinoz, T ^a  

^a NIGDE UNIVERSITY   (Turkey)

^b UNIVERSITY OF THE WEST INDIES   (Jamaica)

Author keywords

Articulatory speech synthesizer; Back propagation algorithm; Statistical dependency of neural learning

Indexed keywords

ACOUSTICS; BACKPROPAGATION; LEARNING SYSTEMS; STATISTICAL METHODS;

ARTICULATORY SPEECH SYNTHESIS;

SPEECH SYNTHESIS;

EID: 0037708380     PISSN: 00457906     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0045-7906(02)00055-1     Document Type: Article

References (13)

1. Ng S.C., Leung S.H., Luk A. Fast convergent generalized back-propagation algorithm with constant learning rate. Neural Process. Lett. 9:1999;13-23.
2. Kim H.B., Jung S.H., Kim T.G., Park K.H. Fast learning-method for backpropagation neural-network by evolutionary adaptation of learning rates. Neurocomputing. 11(1):1996;101-106.
3. Vitela J.E., Reifman J. Premature saturation in backpropagation networks: mechanism and necessary conditions. Neural Networks. 10:1997;712-735.
4. Lee Y., Oh S., Kim M.W. An analysis of premature saturation in back propagation learning. Neural Networks. 6:1993;719-728.
5. Wessel LFA, Banard E. Avoiding false local minima by proper initialization of connections. In: Proc IEEE Trans Neural Networks, Vol. 3, 1992. p. 899-905.
6. Weymaere N, Martens J. On the initialization and optimization of multilayer perceptrons, In: Proc IEEE Trans Neural Networks, Vol. 5, 1994. p. 738-751.
7. Rezgui A, Tepedelenlioglu N. The effect of the slope of the activation function on the back propagation algorithm. In: Proc of Int Joint Conf on Neural Networks, Vol. 1, 1990. p. 707-710.
8. Van Ooyen A., Nienhius B. Improving the Convergence of the BP algorithm. Neural Networks. 5:1992;463-471.
9. Chua H.C., Jia J., Chen L., Gong Y. Solving two-sprial problem through input data encoding. Electron. Lett. 31(10):1995;813-814.
10. Altun H, Yalcinoz T, Tezekici BS. Improvement in the learning process as a function of distribution characteristics of binary data set. In: Proc 10th IEEE Mediterranean Electrotechnical Conference, Melecon, Cyprus 2000, 2000. p. 567-579.
11. Know T.M., Cheng H. Contrast enhancement for backpropagation. IEEE Trans. Neural Networks. 7:1996;515-524.
12. Sorokin V.N., Leonov A.S., Trushkin A.V. Estimation of stability and accuracy of inverse problem solution for the vocal tract. Speech Communication. (30):2000;55-74.
13. Rahim M.G. Artificial neural networks for speech analysis/synthesis. 1995;Chapman and Hall.