Title :
Speech recognition using dynamic recognition neural network
Author :
Zhang Li-Peng ; Li Li-Mei ; Cai Chang-Nian
Author_Institution :
Beijing Univ. of Posts & Telecommun., China
Abstract :
The paper proposes a dynamic recognition neural network model (DRNN), which has the advantages of some neural networks, so it is learns fast, calculates simply, and constructs flexibly. The model is suitable for dynamic recognition, such as speech recognition. Experiments on the Chinese isolated digital recognition were carried out. The results show that the model has potential.<>
Keywords :
learning (artificial intelligence); linguistics; natural languages; neural nets; speech coding; speech recognition; Chinese isolated digital recognition; DRNN; dynamic recognition neural network; speech recognition; Feedforward neural networks; Hidden Markov models; Neural networks; Organizing; Recurrent neural networks; Robustness; Speech recognition; Subspace constraints; Telecommunications; Very large scale integration;
Conference_Titel :
TENCON '93. Proceedings. Computer, Communication, Control and Power Engineering.1993 IEEE Region 10 Conference on
Conference_Location :
Beijing, China
Print_ISBN :
0-7803-1233-3
DOI :
10.1109/TENCON.1993.327990
