Accessibility navigation

Neural network feature maps for Chinese phonemes

Wu, P., Warwick, K. and Moska, M. (1992) Neural network feature maps for Chinese phonemes. Neurocomputing, 4 (1-2). pp. 109-112. ISSN 0925-2312

Full text not archived in this repository.

To link to this item DOI: 10.1016/0925-2312(92)90049-U


It has been shown through a number of experiments that neural networks can be used for a phonetic typewriter. Algorithms can be looked on as producing self-organizing feature maps which correspond to phonemes. In the Chinese language the utterance of a Chinese character consists of a very simple string of Chinese phonemes. With this as a starting point, a neural network feature map for Chinese phonemes can be built up. In this paper, feature map structures for Chinese phonemes are discussed and tested. This research on a Chinese phonetic feature map is important both for Chinese speech recognition and for building a Chinese phonetic typewriter.

Item Type:Article
Divisions:Faculty of Science
ID Code:17882
Uncontrolled Keywords:feature maps, speech processing, phoneme recognition

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation