Abstract
According to Biomimetic Pattern Recognition Theory, this chapter analyses the distribution of different kinds of digit speech in feature space based on Android, and proposes a multi-weight neural network distinction approach. Because this approach takes the inner feature relations of each class of speech samples into full consideration, the neural network constructed can optimal cover each kind of samples. Experiments show the validity of this algorithm.
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
References
Shoujue W (2002) Bionic (Topological) pattern recognition—a new model of pattern recognition theory and its applications. Acta Electronica Sinica, Chinese Institute of Electronics, Beijing, vol 30(10), pp 1417–1420
Jia L (2000) Research on large vocabulary mandarin Chinese continuous speech recognition system. Acta Electronica Sinica, Chinese Institute of Electronics, Beijing, vol 28(1), pp 85–91
Shoujue W, Bainan W (2002) Analysis and theory of high-dimension space geometry for artificial neural networks. Acta Electronica Sinica, Chinese Institute of Electronics, Beijing, vol 30(1), pp 1–4
Rabiner LR, Wilpon G, Soong FK (1989) High performance connected digit recognition using hidden Markov models. IEEE transactions ASSP, IEEE signal processing society, Berlin, Germany, vol 37(8), pp 1214–1225
Junlan F, Limin D (1999) Review on Chinese spontaneous speech recognition. Electronic science & technology review, Chinese Institute of Electronics, Beijing, vol 9, pp 3–7
Smith J, Jones M Jr, Houghton L et al (1999) Future of health insurance. N Engl J Med 965:325–329
Husheng L, Jia L, Runsheng L (2000) High performance digit mandarin speech recognition. J Tsinghua Univ (Sci Technol) 40(1):32–34 (Tsinghua University Beijing, China)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, Y., Li, B. (2013). The Study on Chinese Speech Recognition Based on Android. In: Lu, W., Cai, G., Liu, W., Xing, W. (eds) Proceedings of the 2012 International Conference on Information Technology and Software Engineering. Lecture Notes in Electrical Engineering, vol 212. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34531-9_28
Download citation
DOI: https://doi.org/10.1007/978-3-642-34531-9_28
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34530-2
Online ISBN: 978-3-642-34531-9
eBook Packages: EngineeringEngineering (R0)