A decision-enhanced pattern classifier based on neural network approach

Abstract A pattern classifier employing so-called the auxiliary information to enhance the decision making process is proposed. The distances between each pair of classes are precalculated and saved as the inter-class distances. The auxiliary information is derived from the differences between the distances and the inter-class distances by using the back-propagation learning network. By incorporating the auxiliary information, a decision-enhanced network is constructed to perform the decision making process. The experiments show that the proposed network does improve the performance.

[1]  J. Oglesby,et al.  Optimisation of neural models for speaker identification , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[2]  Biing-Hwang Juang,et al.  Speaker recognition based on source coding approaches , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[3]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[4]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[5]  Stanley C. Ahalt,et al.  Neural Networks for Vector Quantization of Speech and Images , 1990, IEEE J. Sel. Areas Commun..

[6]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[7]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[8]  Michael T. Manry,et al.  Iterative improvement of a Gaussian classifier , 1990, Neural Networks.

[9]  A. Waibel,et al.  Connectionist Viterbi training: a new hybrid method for continuous speech recognition , 1990, International Conference on Acoustics, Speech, and Signal Processing.