Title :
A probabilistic neural network for spatiotemporal pattern recognition
Author :
Wu, Quen-Zong ; Liu, Ron-Yi ; Jeng, Bor-Shenn ; Tsai, Yuang-Chang ; Huang, Su-Shun
Author_Institution :
Telecommun. Lab., Chung-Li, Taiwan
Abstract :
A spatiotemporal probabilistic neural network (SPNN) is proposed for spatiotemporal pattern recognition. Speaker-independent isolated Mandarin digit recognition is used as an example of spatiotemporal pattern recognition. The simulation result shows that SPNN can work quite well for spatiotemporal pattern recognition. The simplicity and effectiveness of SPNN make it suitable for the applications of speech recognition, radar, sonar, etc
Keywords :
neural nets; pattern recognition; probabilistic neural network; radar; sonar; spatiotemporal pattern recognition; speaker-independent isolated Mandarin digit recognition; Laboratories; Multi-layer neural network; Multilayer perceptrons; Neural networks; Neurons; Pattern recognition; Smoothing methods; Spatiotemporal phenomena; Speech recognition; Statistics;
Conference_Titel :
Systems Engineering, 1992., IEEE International Conference on
Conference_Location :
Kobe
Print_ISBN :
0-7803-0734-8
DOI :
10.1109/ICSYSE.1992.236949
