This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
A Default Hierarchy for Pronouncing English
September 1991 (vol. 13 no. 9)
pp. 957-964

The authors study the principles governing the power and efficiency of the default hierarchy, a system of knowledge acquisition and representation. The default hierarchy trains automatically, yet yields a set of rules which can be easily assessed and analyzed. Rules are organized in a hierarchical structure containing general (default) and specific rules. In training the hierarchy, general rules are learned before specific rules. In using the hierarchy, specific rules are accessed first, with default rules used when no specific rules apply. The main results concern the properties of the default hierarchy architecture, as revealed by its application to English pronunciation. Evaluating the hierarchy as a pronouncer of English, the authors find that its rules capture several key features of English spelling. The default hierarchy pronounces English better than the neural network NETtalk, and almost as well as expert-devised systems.

[1] B. MacWhinney, "The acquisition of morphophonology,"Mon. Soc. Res. Child Develop., vol. 43, nos. 1-2, 1978.
[2] M. R. Quillian, "Semantic memory," inSemantic Information Processing. M. Minsky, Ed. Cambridge, MA: MIT Press, 1968, pp. 216-270.
[3] S. E. Fahlman,NETL: A System for Representing and Using Real-World Knowledge. Cambridge, MA: MIT Press, 1979.
[4] R. Brachman, "On the epistemological status of semantic networks," inAssociative Networks: Representation and Use of Knowledge by Computers, N. V. Findler, Ed. New York: Academic, 1979, pp. 3-50.
[5] R. Reiter, "A logic for default reasoning,"Artificial Intell., vol. 13, pp. 81-132, 1980.
[6] M. Minsky, "A framework for representing knowledge," inMind Design, J. Haugeland, Ed. Cambridge, MA: MIT Press, 1981, pp. 95-128.
[7] D. S. Touretzky, "Implicit ordering of defaults in inheritance systems," inProc. AAAI-13, 1984, pp. 322-325.
[8] J. H. Holland,Adaptation in Natural and Artificial Systems. Ann Arbor, MI: University of Michigan Press, 1975.
[9] S. M. Minszewski and S. C. Clearwater, "A symbolic default hierarchy of higher-order correlation neural networks for accelerator diagnostics," Los Angeles Nat. Lab., Rep. LA-UR #90-2019, 1990.
[10] Z. G. An, S. M. Mniszewski, Y. C. Lee, G. J. Papcun, and G. D. Doolen, "HIERTALKER: A default hierarchy of high order neural networks that learns to read aloud," inProc. IEEE Int. Conf. Neural Networks, vol. II, pp. 221-228, 1988.
[11] D. H. Klatt, "The Klattalk text-to-speech system," inProc. Int. Conf. Acoustics Speech Signal Processing, IEEE Catalog No. 82CH1746-7, 1982, pp. 1589-1592.
[12] H. S. Elovitz, R. Johnson, A. McHugh, and J. E. Shore, "Letter-to-sound rules for automatic translation of English text to phonetics," inIEEE Trans. Acoust. Speech Signal Processing, vol. ASSP-24, pp. 446-459, 1976.
[13] T. J. Sejnowski and C. R. Rosenberg, "Parallel networks that learn to pronounce English text,"Complex Syst., vol. 1, pp. 145-168, 1987.
[14] M. Seidenberg and J. L. McClelland, "A distributed, developmental model for word recognition and naming,"Psychol. Rev., vol. 96, pp. 523-568, 1989.
[15] R. L. Venezky,The Structure of English Orthography. The Hague, The Netherlands: Mouton, 1970.
[16] L. Bloomfield,Language. New York: Holt, Rinehart&Winston, 1933.
[17] A. R. Davis, A. Karamchandani, and G. Papcun, "Acceptance thresholds for decision and recognition systems: A case study," Los Alamos Nat. Lab., Rep. LA-UR #90-1614, 1990.
[18] R. Meddis,Statistics Using Ranks. Oxford, England: Blackwell, 1984.
[19] S. Hunnicutt, "Phonological rules for a text-to-speech system,"Amer. J. Computat. Linguistics, Microfiche 57, 1976.
[20] C. Stanfil and D. Waltz, "Toward memory-based reasoning,"Commun. ACM, vol. 29, pp. 1213-1228, 1986.
[21] H. Kuchera and W. N. Francis,Computational Analysis of Modern-Day American English. Providence, RI: Brown University Press, 1967.

Index Terms:
knowledge representation; speech synthesis; speech intelligibility; learning systems; default hierarchy; knowledge acquisition; default rules; English pronunciation; spelling; knowledge acquisition; knowledge representation; learning systems; natural languages; speech intelligibility; speech synthesis
Citation:
J. Hochberg, S.M. Mniszewski, T. Calleja, G.J. Papcun, "A Default Hierarchy for Pronouncing English," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 9, pp. 957-964, Sept. 1991, doi:10.1109/34.93813
Usage of this product signifies your acceptance of the Terms of Use.