Abstract
Two-weight neural network (TWNN) is described in this paper. Anew dynamic searching algorithm based on Two-weight neural network is presented. And then it is applied to recognize the Continuous Speech of Speaker-Independent. The recognition results can be searched dynamically without endpoint detecting and segmenting. Different feature-space covers are constructed according to different classes of syllables. Compared with the conventional HMM-based method, The trend of recognition results shows that the difference of recognition rates between these two methods decreases as the number of training increases, but the recognition rate of Two-weight neural network is always higher than that of HMM-based. And both of these recognition rates will reach 100% if there are enough training samples.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Yang, W.-J.: Hidden Markov Model for Mandarin Lexical Tone Recognition. IEEE Trans. Acoust. Speech Signal Process 36, 988–992 (1988)
Chen, X.-X., Cai, C.-N., Guo, P., Sun, Y.A.: Hidden Markov Model Applied to Chinese Four-tone Recognition. In: Proc. International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 797–800 (1987)
Lee, L.S.: Voice Dictation of Mandarin Chinese. IEEE Signal Processing 14(4), 63–101 (1997)
Chen, S.H., Wang, Y.R.: Tone Recognition of Continuous Mandarin Speech Based on Neural Networks. IEEE Trans. Speech Audio Process 3, 146–150 (1995)
Wang, S.: Biomimetic (Topological) Pattern Recognition - A New Model of Pattern Recognition Theory and Its Applications (in Chinese). Acta Electronica Sinica 30, 1417–1420 (2002)
Wang, S.: Biomimetics Pattern Recognition. Neural Networks Society (INNS, ENNS, JNNS) Newsletter 1, 3–5 (2003)
Cao, W., Feng, H., Wang, S.: The Application of DBF Neural Networks for Object Recognition. Inf. Sci. 160, 153–160 (2004)
Cao, W.: The Application of Direction Basis Function Neural Networks to the Prediction of Chaotic Time Series. Chinese Journal of Electronics 13, 395–398 (2004)
Cao, W., Feng, H., Zhang, D.M., et al.: An Adaptive Controller for a Class of Nonlinear System Using Direction Basis Function. Chinese Journal Of Electronics 11, 303–306 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cao, W., Pan, X., Wang, S. (2005). Continuous Speech Research Based on Two-Weight Neural Network. In: Wang, J., Liao, XF., Yi, Z. (eds) Advances in Neural Networks – ISNN 2005. ISNN 2005. Lecture Notes in Computer Science, vol 3497. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11427445_56
Download citation
DOI: https://doi.org/10.1007/11427445_56
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25913-8
Online ISBN: 978-3-540-32067-8
eBook Packages: Computer ScienceComputer Science (R0)