Time-Delayed Recurrent Neural Network for Temporal Correlations and Prediction, and its Application to Phone Recognition
Sung-Suk Kim, Kwang‐Hee Kim, Chong-Koo An, Won‐Ho Choi, Tai-Ho Lee · Journal of Electrical Engineering and Information Science · 1999
This paper presents a Time-Delayed Recurrent Neural Network (TDRNN) for temporal correlations and prediction, and its application to phone recognition, The TDRNN employs adaptive time-delays and recurrences where the adaptive time-delays make the network choose the optimal values of time-delays for the temporal location of the important information in the input sequence and the recurrences enable the network to encode and integrate temporal context information of sequences. The TDRNN and Multiple Recurrent Neural Network(MRNN) described in tills paper, Adaptive Time-Delay Neural Network (ATNN) proposed by Lin, and Time-Delay Neural Network (TDNN) introduced by Waibel were simulated and applied to the chaotic time series prediction of Mackey-Glass delay-differential equation, the Korea stock market index prediction, and the phone recognition. The simulation results suggest that employing time-delayed recurrences between layer in the network is more effective for temporal correlations, prediction, and recognition than putting multiple time-delays into the neurons or their connections. The best performance is attained by the TDRNN. The TDRNN will be well applicable for temporal signal recognition, prediction and identification.