ISCA Archive ICSLP 1994
ISCA Archive ICSLP 1994

A continuous HMM based preprocessor for modular speech recognition neural networks

Fikret S. Gurgen, J. M. Song, R. W. King

This paper uses a speech recognition method which combines a continuous density hidden Markov model (CDHMM)-based preprocessor with window-based neural network (WNN) architectures. The method also employs modularity of NNs. It removes fixed-sized input constraint of NN and improves recognition performance. The CDHMM preprocessor performs a priori Gaussian shaping and normalization using statistically modelled state vectors in contrast to simple distance metric between acoustic vectors in dynamic time warping (DTW) preprocessor. Then, normalized and a priori Gaussian shaped speech features are applied as input to WNN and modular WNN architectures. NIST TI-46 E-set experiments are performed and the results are compared with a baseline CDHMM results. The proposed system improves the recognition performance. Modular WNN provides further significant improvement on the performance.


Cite as: Gurgen, F.S., Song, J.M., King, R.W. (1994) A continuous HMM based preprocessor for modular speech recognition neural networks. Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994), 1507-1510

@inproceedings{gurgen94_icslp,
  author={Fikret S. Gurgen and J. M. Song and R. W. King},
  title={{A continuous HMM based preprocessor for modular speech recognition neural networks}},
  year=1994,
  booktitle={Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994)},
  pages={1507--1510}
}