Title :
The consonant/vowel (C/V) speech classification using high-rank function neural network (HRFNN)
Author :
Minghu, Jiang ; Baozong, Yuan ; Biqin, Lin
Author_Institution :
Inst. of Inf. Sci., Northern Jiaotong Univ., Beijing, China
Abstract :
The article provide an improvement of the method of Bendiksen et. al. (1990) adopting the backpropagation (BP) network for voiced/unvoiced speech classification, by using the HRFNN, adapting it to the non-linear pronunciation model. The comparison test has shown that the HRFNN has a 100 times higher training rate than the BP network and the recognition accuracy is better than the BP network. As for the dynamic time-changing characterization of the speech signals and non-right-cross distribution of the C/V features, it was very difficult to search for the accurate CV transforming point in the past. A time-delay HRFNN is put forward, it is very effective for recognition of the CV transforming point, and for the automatic segmentation of continuous speech, it has a fast training rate, high recognition accuracy, and good dynamic characterization. The theory and experiments have shown that the network model is of high robustness
Keywords :
delays; learning (artificial intelligence); neural nets; speech processing; speech recognition; CV transforming point; HRFNN; automatic segmentation; backpropagation network; consonant/vowel speech classification; continuous speech; dynamic characterization; dynamic time-changing characterization; experiments; high-rank function neural network; neural network model; nonlinear pronunciation model; nonright-cross distribution; recognition accuracy; speech signals; time-delay HRFNN; training rate; Autocorrelation; Convergence; Delay; Digital signal processing; Equations; Filters; Neural networks; Neurons; Speech; Testing;
Conference_Titel :
Signal Processing, 1996., 3rd International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-2912-0
DOI :
10.1109/ICSIGP.1996.571146