Neural Net Pattern Recognition Equations with Self-organization for Phoneme Recognition
In this paper, the neural net pattern recognition equations were attempted to apply to speech recognition. The proposed method features a dynamic process of self-organization that has been proved to be successful in recognizing a depth perception in stereoscopic vision. This study showed that the dynamic process was also useful in recognizing human speech. In the processing, input vocal signals are first compared with standard models to measure similarities that are then given to the dynamic process of self-organization. The competitive and cooperative processes are conducted among neighboring input similarities, so that only one winner neuron is finally detected. In a comparative study, it showed that the proposed method outperformed the conventional Hidden Markov Models(HMM) speech recognizer under the same conditions.
KeywordsHide Markov Model Speech Recognition Depth Perception Stereo Vision Speech Database
Unable to display preview. Download preview PDF.
- Woodland, P.C., Leggestter, C.J., Odell, J.J., et al.: The 1994 HTK Large Vocabulary Speech Recognition System. In: Proc. IEEE Int. Con. on Acoustics, Speech, and Signal Processing, vol. 1, pp. 73–76 (1995)Google Scholar
- Lang, J., Waibel, A., Hinton, G.E.: A Time-Delay Neural Network Architecture for Isolated Word Recognition. In: Artificial Neural Networks, Paradigms, Applications and Hardware Implementations, pp. 388–408. IEEE press, New York (1992)Google Scholar
- Yoshitomi, Y., Kanda, T., Kitazoe, T.: Neural Nets Pattern Recognition Equation for Stereo Vision. Trans. IPS, 29–38 (1998)Google Scholar