A Segmentation Method for Continuous Speech Utilizing Hybrid Neuro-Fuzzy Network.
作者： Eugene Lai , Mu-Chun Su , Chih-Hsu Hsu , Ching-Tang Hsieh
关键词:
摘要: This paper presents a hierarchical neuro-fuzzy network system for segmenting continuous speech into syllables. The formulates segmentation as two-phase procedure. In the first phase, Hybrid Neuro-Fuzzy (HNFN) is utilized to classify signal three different types. hybrid model composed of distributed representation fuzzy (DRF) and hyperrectangular composite neural (HRCNN) proposed used cluster frames. special may neutralize disadvantages each alternative. parameters in trained HNFN are extract both crispy classification rules. following self-tuning back-propagation (STBNN) solve coarticulation effects vowel-vowel (V-V) concatenation. our experiments, database containing reading-rate Mandarin recorded from newscasts was test performance speaker-independent system. effectiveness confirmed by experimental results.
sci-hub.st 参考文章(6)
Shih-Chieh Chien, Ching-Tang Hsieh, Speech Segmentation and Clustering Problem based on Fuzzy Rules and Transition States. Applied Informatics. pp. 291- 294 ,(1994)
Ching-Tang Hsieh, Mu-Chun Su, Shih-Chieh Chienn, Use of a self-learning neuro-fuzzy system for syllabic labeling of continuous speech ieee international conference on fuzzy systems. ,vol. 4, pp. 1727- 1734 ,(1995) , 10.1109/FUZZY.1995.409915
L. R. Rabiner, M. R. Sambur, An Algorithm for Determining the Endpoints of Isolated Utterances Bell System Technical Journal. ,vol. 54, pp. 297- 315 ,(1975) , 10.1002/J.1538-7305.1975.TB02840.X
Hisao Ishibuchi, Ken Nozaki, Hideo Tanaka, Distributed representation of fuzzy rules and its application to pattern classification Fuzzy Sets and Systems. ,vol. 52, pp. 21- 32 ,(1992) , 10.1016/0165-0114(92)90032-Y
Tarek M. Nabhan, Albert Y. Zomaya, Toward generating neural network structures for function approximation Neural Networks. ,vol. 7, pp. 89- 99 ,(1994) , 10.1016/0893-6080(94)90058-2