Continuous Speech Recognition Based on ICA and Geometrical Learning
We investigate the use of independent component analysis (ICA) for speech feature extraction in digits speech recognition systems. We observe that this may be true for recognition tasks based on Geometrical Learning with little training data. In contrast to image processing, phase information is not essential for digits speech recognition. We therefore propose a new scheme that shows how the phase sensitivity can be removed by using an analytical description of the ICA-adapted basis functions. Furthermore, since the basis functions are not shift invariant, we extend the method to include a frequency-based ICA stage that removes redundant time shift information. The digits speech recognition results show promising accuracy. Experiments show that the method based on ICA and Geometrical Learning outperforms HMM in a different number of training samples.
KeywordsDiscrete Cosine Transform Recognition Rate Independent Component Analysis Speech Recognition Speech Signal
Unable to display preview. Download preview PDF.
- 1.Amari, S.: Neural learning in structured parameter spaces—natural Riemannian gradient. In: Advances in Neural Information Processing System, vol. 9, pp. 127–133. MIT Press, Cambridge (1997)Google Scholar
- 6.Lee, J.H., Jung, H.Y., Lee, T.W., Lee, S.Y.: Speech feature extraction using independent component analysis. In: Proceedings of the International Conference Acoustics, Speech, Signal Processing, Istanbul, Turkey, June 2000, pp. 1631–1634 (2000)Google Scholar
- 8.ShouJue, W.: A new development on ANN in China - Biomimetic pattern recognition and multi weight vector neurons. LNCS (LNAI), vol. 2639, pp. 35–43. Springer, Heidelberg (2003)Google Scholar
- 9.Shoujue, W., et al.: Multi Camera Human Face Personal Identification System Based on Biomimetic pattern recognition. Acta Electronica Sinica 31(1), 1–3 (2003)Google Scholar
- 10.Shoujue, W., et al.: Discussion on the basic mathematical models of Neurons in General purpose Neurocomputer. Acta Electronica Sinica 29(5), 577–580 (2001)Google Scholar
- 16.Cao, W.M.: The application of Direction basis function neural networks to the prediction of chaotic time series. Chinese Journal of Electronics 13(3), 395–398 (2004)Google Scholar