Title :
Application of Novel Chaotic Neural Networks to Mandarin Digital Speech Recognition
Author :
Zhang, Jin ; Li, Guang ; Freeman, Walter J.
Author_Institution :
Zhejiang Univ., Hangzhou
Abstract :
To model mammalian olfactory neural systems, a chaotic neural network entitled k-set has been constructed. This neural network with non-convergent "chaotic" dynamics simulates biological pattern recognition. This paper reports the characteristics of the KIII set and applies it to digital classification of the sounds of Mandarin spoken digits. Experimental results show that the KIII set performs digital speech recognition efficiently.
Keywords :
chaos; chemioception; neural nets; speech recognition; speech synthesis; Mandarin digital speech recognition; biological pattern recognition; chaotic neural networks; digital speech recognition; mammalian olfactory neural systems; Biological system modeling; Brain modeling; Chaos; Electroencephalography; Hidden Markov models; Negative feedback; Nerve fibers; Neural networks; Olfactory; Speech recognition;
Conference_Titel :
Neural Networks, 2006. IJCNN '06. International Joint Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-9490-9
DOI :
10.1109/IJCNN.2006.246745