Browse > Article

Speech Recognition by Neural Net Pattern Recognition Equations with Self-organization  

Kim, Sung-Ill (Division of Electrical and Electronic Engineering, Kyungnam University)
Chung, Hyun-Yeol (School of Electrical Engineering and Computer Science, Yeungnam University)
Publication Information
The Journal of the Acoustical Society of Korea / v.22, no.2E, 2003 , pp. 49-55 More about this Journal
Abstract
The modified neural net pattern recognition equations were attempted to apply to speech recognition. The proposed method has a dynamic process of self-organization that has been proved to be successful in recognizing a depth perception in stereoscopic vision. This study has shown that the process has also been 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 a process of self-organization in neural net equations. 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 neural networks outperformed the conventional HMM speech recognizer under the same conditions.
Keywords
Speech recognition; Coupled pattern recognition; Neural network; HMM; Depth perception;
Citations & Related Records
연도 인용수 순위
  • Reference
1 X. D. Huang, Y. Ariki, and M. A. Jack, Hidden Makov Models for Speech Recognition, Edinburgh University Press, Edinburgh, U. K., 1990
2 C. J. Bourlard, and Wellekens. 'Links between Markov models and multi-layer perceptrons,' IEEE Trans. Patt. Anal. Machine Intell., 12, 1167-1178, 1990   DOI   ScienceOn
3 T. Waibel, G. Hanazawa, K. Hinton, Shikano et al., 'Phoneme recognition using time-delay neural networks,' IEEE Trans. on Acoustics, Speech and Signal Processing, 37 (3), 329-339, 1989
4 Y. Yoshitomi, T. Kitazoe, J. Tomiyama and Y. Tatebe, 'Sequential stereo vision and phase transition,' Proc. of Third Int. Symp. On Artificial Lile, and Robotics, 318-323, 1998
5 S. Amari, and M. A. Arbib, 'Competition and cooperation in neural nets,' Systems Neuroscience, 119-165, Academic Press, 1977
6 D. Reinmann, H. Haken, 'Stereo vision by self-organization,' Biol. Cybern., 71, 17-26, 1994   DOI   ScienceOn
7 Martinelli, 'Hidden control neural network,' IEEE Trans on Circuits and Systems, Analog and Signal Processing, 41 (3), 245-247, 1994
8 T. Kitazoe, S-I Kim, and T. Ichiki, 'Speech Recognition using Stereovision Neural Network Model,' Proc. International Symposium on Artificial Life and Robotics, 2, 576-579, 1999
9 T. Kitazoe, J. Tomiyama, Y. Yoshitomi, et al., 'Sequential stereoscopic vision and hysteresis,' Proc. Neural Information Processing, 391-396, 1998
10 L. Rabiner, A Tutorial 'Hidden Markov models and selected applications in speech recognition,' A. Waibel and K.-F. Lee, editors, Readings in Speech Recognition, 267-296, Morgan Kaufmann, San Mateo, 1990
11 T. Kitazoe, S.-I. Kim, and T. Ichiki, 'Acoustic speech recognition by two and three layered neural networks with competition and cooperation,' Proceeding of International Workshop on Speech and computer, 111-114, 1999
12 D. Reimann, T. Ditzinger, E. Fischer, and H. Haken, 'Vergence eye movement control and multivalent perception of Autostereograms,' Biol. Cybern. 73, 123-128, 1995   DOI   ScienceOn
13 T. Kohonen, 'Self-organizing map,' Proc. IEEE, 78 (9), 1464-1480, 1990   DOI   ScienceOn
14 P. C. Woodland, C. J. Leggestter, J. J. Odell, V. Valtchev, and S. J. Young. 'The 1994 HTK large vocabulary speech recognition system,' Proc. IEEE Int. Conf. On Acoustics, Speech, and Signal Processing, 1, 73-76, Detroit, 1995
15 Y. Yoshitomi, T. Kanda, and T. Kitazoe, 'Neural nets pattern recognition equation for stereo vision,' Trans. IPS, 29-38, 1998