This Article 
 Bibliographic References 
 Add to: 
A Hybrid Model for the Prediction of the Linguistic Origin of Surnames
May/June 2003 (vol. 15 no. 3)
pp. 760-763

Abstract—The prediction of the linguistic origin of surnames is a basic functionality required in the design of high-quality multilanguage speech synthesizers. The assignment of a given string representing a surname to a specific language is typically based on a set of rules which can hardly be written in an explicit form. The approach we propose faces this problem combining a rule-based system with a module based on evidential reasoning and a module based on neural networks. The resulting hybrid system combines the different sources of information, merging both knowledge from experts on linguistics and knowledge automatically acquired using learning from examples. The system has been validated on a large database containing surnames belonging to four different languages, showing its effectiveness for real-world applications.

[1] K. Belhoula, “A Concept for Synthesis of Names,” Proc. Joint ESCA-NATO/RSG 10 Tutorial and Workshop Applications of Speech Technology, pp. 167-170, Sept. 1993.
[2] R. Carlson, B. Granström, and A. Linsdström, “Predicting Name Pronunciation for a Reverse Directory Service,” Proc. European Conf. Speech Technology, vol. 1, pp. 113-116, Sept. 1989.
[3] K. Church, “Stress Assignment in Letter to Sound Rules for Speech Synthesis,” Proc. IEEE Int'l Conf. Acoustics, Speech and Signal Processing (ICASSP '86), vol. 4, pp. 2423-2426, 1986.
[4] B. Van Coile, S. Leys, and L. Mortier, “On the Development of a Name Pronunciation System,” Proc. Int'l Conf. Spoken Language Processing (ICSLP-92), vol. 1, pp. 487-490, Oct. 1992.
[5] T. Vitale, “An Algorithm for High Accuracy Name Pronunciation by Parametric Speech Synthesizer,” Computational Linguistic, vol. 17, no. 3, pp. 257-276, 1991.
[6] T. Dutoit, An Introdution to Text-to-Speech Synthesis. Kluwer Academic, 1997.
[7] J. Ngam, A. Ganapathiraju, and J. Picone, “Improved Surname Pronunciation Using Decision Trees,” Proc. Int'l Conf. Spoken Language Processing (ICSLP-98), pp. 2923-2926, 1998.
[8] G. Shafer, A Mathematical Theory of Evidence. Princeton Univ. Press, 1976.
[9] R.R. Yager, J. Kacprzyk, and M. Fedrizzi, Advances in the Dempster-Shafer Theory of Evidence. John Wiley&Sons, 1994.
[10] L.A. Zadeh, “A Simple View of Dempster-Shafer Theory of Evidence and Its Implication for the Rule of Combination,” The AI Magazine, vol. 7, no. 2, pp. 85-90, 1986.
[11] O NOMASTICA, “Creating a Multi-Lingual Dictionary of European Names,” Final Technical Report Linguistic Research and Eng. Programme—Project No. LRE-61004, European Community, 30 May 1995.
[12] D.E. Rumelhart, G.E. Hinton, and R.J. Williams, "Learning Internal Representations by Error Propagation," Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1: Foundations, D.E. Rumelhart and J.L. McClelland et al., eds., chapter 8, pp. 318-362.Cambridge, Mass.: MIT Press, 1986.

Index Terms:
Dempster-Shafer's theory, hybrid systems, neural networks, speech synthesizers, surname classification.
Patrizia Bonaventura, Marco Gori, Marco Maggini, Franco Scarselli, Jianqing Sheng, "A Hybrid Model for the Prediction of the Linguistic Origin of Surnames," IEEE Transactions on Knowledge and Data Engineering, vol. 15, no. 3, pp. 760-763, May-June 2003, doi:10.1109/TKDE.2003.1198404
Usage of this product signifies your acceptance of the Terms of Use.