Connected Word Recognition Using Neural Networks
作者： Umit Dağitan , Neşe Yalabik
DOI: 10.1007/978-3-642-76153-9_34
关键词:
摘要: A connected word recognition system which makes use of two neural network models, namely, Kohonen’s Network and a Multilayer Perceptron is implemented. The digitized speech signal represented by sequence Linear Predictive Coding (LPC) coefficients segmented into syllables. used to perform vector quantization compress LPC data for the input (MP). MP in syllable basis with Back-Propagation algorithm training. words are constructed using recognized was trained tested ten Turkish sixteen syllables, an overall rate 90 percent.
springer.com
sci-hub.st 参考文章(5)
David E. Rumelhart, James L. McClelland, , Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations Computational Models of Cognition and Perception. ,(1986) , 10.7551/MITPRESS/5236.001.0001
Paul Mermelstein, Automatic segmentation of speech into syllabic units Journal of the Acoustical Society of America. ,vol. 58, pp. 880- 883 ,(1975) , 10.1121/1.380738
Y. Bengio, R. Cardin, R. De Mori, E. Merlo, Programmable execution of multi-layered networks for automatic speech recognition Communications of the ACM. ,vol. 32, pp. 195- 199 ,(1989) , 10.1145/63342.63345
D.J. Burr, Experiments on neural net recognition of spoken and written text IEEE Transactions on Acoustics, Speech, and Signal Processing. ,vol. 36, pp. 1162- 1168 ,(1988) , 10.1109/29.1643
D. E. Rumelhart, G. E. Hinton, R. J. Williams, Learning internal representations by error propagation Parallel distributed processing: explorations in the microstructure of cognition, vol. 1. ,vol. 1, pp. 318- 362 ,(1986)