This paper presents a procedure of frame normalization based on the traditional dynamic time warping (DTW) using the LPC coefficients. The redefined method is called as the DTW frame-fixing method (DTW-FF), it works by normalizing the word frames of the input against theudreference frames. The enthusiasm to this study is due to neural network limitation that entails a fix number of input nodes for when processing multiple inputs in parallel. Due to this problem, this research is initiated to reduce the amount of computation and complexity in a neural network by reducing the number of inputs into the network. In this study, dynamic warping process is used, in which local distance scores of the warping path are fixed and collected so that their scores are of equal number of frames. Also studied in this paper is theudconsideration of pitch as a contributing feature to the speech recognition. Results showed a good performance andudimprovement when using pitch along with DTW-FF feature.udThe convergence rate between using the steepest gradientuddescent is also compared to another method namely conjugateudgradient method. Convergence rate is also improved whenudconjugate gradient method is introduced in the back-propagation algorithm.
展开▼
