This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
A Parallel Computational Model for Integrated Speech and Natural Language Understanding
October 1993 (vol. 42 no. 10)
pp. 1171-1183

Presents a parallel approach for integrating speech and natural language understanding. The method emphasizes a hierarchically-structured knowledge base and memory-based parsing techniques. Processing is carried out by passing multiple markers in parallel through the knowledge base. Speech specific problems such as insertion, deletion, substitution, and word boundary detection have been analyzed and their parallel solutions are provided. Results on the SNAP-1 multiprocessor show an 80% sentence recognition rate for the Air Traffic Control (ATC) domain. Furthermore, speed-up of up to 15-fold is obtained from the parallel platform which provides response times of a few seconds per sentence for the ATC domain.

[1] M. T. Anikst and D. J. Trawick, "Training continuous speech linguistic decoding parameters as a single-layer perceptron.Proc. Int. Joint Conf. on Neural Networks, vol. 2, pp. 237-240, 1990.
[2] M. Chung and D. I. Moldovan, "Memory-based parsing on SNAP: Integrated syntactic and semantic analysis," Tech. Report PKPL 91-10, Dept. of Elect. Eng. Syst., Univ. of Southern California, Los Angeles, 1991.
[3] M. Chung and D. I. Moldovan, "Modeling semantic networks on the connection machine,"J. Parallel and Distributed Computing, vol. 17, pp. 152-163, Feb. 1993.
[4] R. Demara and D. Moldovan, "The SNAP-1 Parallel AI Prototype,"Proc. 18th Ann. Int'l Symp. Computer Architecture, IEEE CS Press, Los Alamitos, Calif., Order No. 2146, 1991, pp. 2-11.
[5] S. E. Fahlman,NETL: A System for Representing and Using Real-World Knowledge. Cambridge, MA: MIT Press, 1979.
[6] E. P. Giachin and C. Rullent, "A parallel parser for spoken natural language,"Proc. IJCAL, 1989, pp. 1537-1542.
[7] P. J. Hayes, A. G. Hauptmann, J. G. Carbonell, and M. Tomita, "Parsing spoken language: A semantic caseframe approach,"Proc. COLING-86, 1986, pp. 587-592.
[8] J.A. Hendler,Integrating Marker-Passing and Problem-Solving, Lawrence Erlbaum Associates, Hillsdale, N.J., 1988.
[9] X. Huang and L. Guthrie, "Parsing in parallel,"Proc. COLING-86, 1986, pp. 140-145.
[10] H. Kitano, "ΦDM-Dialog: A speech-to-speech dialogue translation system,"Machine Translation, vol. 5, pp. 301-338, 1990.
[11] K. F. Lee, "Large-vocabulary speaker-independent continuous speech recognition: The sphinx system," Techn. Rep. CMU-CS-88-148, Dept. of Comput. Sci., Carnegie-Mellon Univ., Pittsburgh, PA, 1988.
[12] W. S. Meisel, M. P. Fortunato, and W. D. Michalek, "A phonetically-based speech recognition system,"Speech Technol., Apr./May 1989.
[13] L. Olorenshaw, "Air traffic control training using continuous speech recognition and the ATCOACH," presented atProc. Speech Tech '90, 1990.
[14] A. Paeseler, "Modification of Earley's algorithm for speech understanding,"Recent Advances in Speech Understanding and Dialog Systems. Berlin: Springer-Verlag, 1987.
[15] C. Riesbeck and R. Schank,Inside Case-Based Reasoning, Lawrence Erlbaum Associates, 1989.
[16] C. K. Riesbeck and C. E. Martin, "Direct memory access parsing," Tech. Rep. YALEU/DCS/RR #354, Dept. of Comput. Sci., Yale Univ., 1985.
[17] C. Stanfil and D. Waltz, "Toward memory-based reasoning,"Commun. ACM, vol. 29, pp. 1213-1228, 1986.
[18] S. Seneff, "TIMA: A probabilistic syntactic parser for speech understanding systems,"Proc. DARPA Speech and Natural Language Workshop, 1989, pp. 168-178.
[19] H. Tomabechi, "Direct memory access translation,"Proc. IJCAI, 1987, pp. 722-725.
[20] D. L. Waltz and J. B. Pollack, "Massively parallel parsing: A strong interactive model of natural language interpretation,"Cognitive Sci., vol. 9, pp. 51-74, 1985.
[21] S.R. Young et al., "High-Level Knowledge Sources in Usable Speech Recognition Systems,"Comm. ACM, Vol. 32, Feb. 1989, pp. 183-194.

Index Terms:
parallel computational model; natural language understanding; speech; hierarchically-structured knowledge base; memory-based parsing; knowledge base; SNAP-1 multiprocessor; knowledge based systems; natural languages; parallel processing; speech.
Citation:
Sang-Hwa Chung, D.I. Moldovan, R.F. DeMara, "A Parallel Computational Model for Integrated Speech and Natural Language Understanding," IEEE Transactions on Computers, vol. 42, no. 10, pp. 1171-1183, Oct. 1993, doi:10.1109/12.257704
Usage of this product signifies your acceptance of the Terms of Use.