Abstract
The object of this review and position paper is to draw a parallel between the field of high-performance speech recognition systems on one side and the field of computer systems (in particular computer systems for Artificial Intelligence applications) on the other. This paper gives a characterization of the computational requirements of speech recognition systems, and describes and exemplifies the classes of machines that could be useful in speeding up speech recognition systems.
This research was sponsored by the Defense Advanced Research Projects Agency (DOD), ARPA Order No. 3597, monitored by the Air Force Avionics Laboratory Under Contract F33615-81-K-1539.
The views and conclusions contained in this document are those of the author and should not be interpreted as representing the official policies, either expressed or implied, of the Defense Advanced Research Projects Agency or the US Government.
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
Speech Group, Summary of Results of the Five-year Research Effort at Carnegie-Mellon University, Computer Science Department, Carnegie-Mellon University, 1977.
R. A. Iannucci Arvind, “A critique of multiprocessing von Neumann style,” 10th Annual International Symposium on Computer Architecture, 1983.
T. Anantharaman, M. Annaratone, R. Bisiani, “A family of custom VLSI circuits for speech recognition,” IEEE International Conference on Acoustics, Speech and Signal Processing, March 1984.
R. Bisiani, H. Mauersberg and R. Reddy, “Task-oriented architectures,” Proceedings of the IEEE, July 1983.
H. Boley, “A preliminary survey of artificial intelligence machines,” SIGART, 72, July 1980.
R. A. Kavaler, T. G. Noll, M. Lowy, H. Murveit and R. W. Brodersen, “A dynamic time warp IC for a one thousand recognition system,” ICASSP ’84, IEEE, San Diego, March 1984.
R. D. Fellman and R. W. Brodersen, “A switched capacitor adaptive lattice filter,” Journal of Solid State Circuits, February 1983.
R. A. Cole, R. M. Stern, M. S. Phillips, S. M. Brill, P. Specker, and A. P. Pilant, “Feature-based speaker-independent recognition of English letters,” ICASSP ’83 Proceedings, IEEE, 1983, pp. 731–734.
W. D. Hillis, The Connection Machine, MIT, 1981.
R. De Mori, R. Giordana, A. Laface, P. Saitta, “Parallel algorithms for syllable recognition in continuous speech,” to be published.
L. D. Erman, F. Hayes-Roth, V. R. Lesser, D. R. Reddy, “The Hearsay-II speech-understanding system: integrating knowledge to resolve uncertainty,” ACM Computing Surveys, 12, 2, June 1980.
S. E. Fahlman, NETL: A system for representing and using real world knowledge, Ph. D. Th., MIT, 1979.
P. Frison and P. Quinton, “A VLSI parallel machine for speech recognition,” ICASP ’84, IEEE, San Diego, March 1984.
R. G. Goodman, Language design for man-machine communication, Ph. D. Th., Carnegie-Mellon University, 1976.
R. Greenblatt, T. Knight and J. Holloway, A LISP Machine, Fifth Workshop on Architectures for Non-numeric Processing, Asilomar, March 1980.
A. Gupta and C. L. Forgy, Measurements on Production Systems, Carnegie-Mellon University, 1983.
S. E. Fahlman, G. E. Hinton and T. J. Sejnowski, “Massively parallel architectures for AI: NETL, THISTLE and Boltzmann machines,” AAAI-83, AAAI, Washington, DC, 1983.
L. R. Bahl, Das Das, P. V. De Souza, F. Jelinek, S. Katz, R. L. Mercer, M. A. Picheny, “Some experiments with large-vocabulary isolated word sentence recognition,” ICASSP ’84, IEEE, San Diego, March 1984.
J. N. Holmes, “The JSRU channel vocoder,” IEEE Proceedings 127, February 1980.
G. E. Kopec, “The integrated signal processing system ISP,” ICASSP ’84, IEEE, San Diego, March 1984.
B. T. Lowerre, The Harpy Speech Recognition System, Ph. D. Th., Computer Science Department, Carnegie-Mellon University, 1976.
J. Makhoul, “Linear prediction: A tutorial review,” Proc. IEEE 63, April 1975.
K. Oflazer, Partitioning in Parallel Processing of Production Systems, Computer Science Dept., Carnegie-Mellon University, Thesis Proposal 1984.
P. N. Oleinick, The Implementation and Evaluation of Parallel Algorithms on C.mmp. Ph. D. Th., Carnegie-Mellon University, Computer Science Department, 1978.
L. R. Rabiner, A. E. Rosenberg, S. E. Levinson, “Considerations in dynamic time-warping algorithms for discrete word recognition,” IEEE Trans. ASSP ASSP-26, 6, December 1978.
D. W. Shipman, “SpireX: statistical analysis in the spire acoustic-phonetic workstation,” ICASSP ’83, IEEE, March 1983.
S. Stolfo, D. Miranker and D. F. Shaw, “Architecture and applications of DADO: A large scale parallel computer for artificial intelligence,” International Joint Conference on Artificial Intelligence, 1983.
R. J. Swan, The Switching Structure and Addressing Architecture of an Extensible Multiprocessor: Cm*, Ph. D, Th., Carnegie-Mellon University, Computer Science Department, August 1978.
A. Gottlieb, C. P. Grishman, K. P. Kruskal, L. McAuliffe, L. Rudolph, “The NYU ultracomputer — designing an MIMD shared memory parallel computer,” IEEE Trans, on Computers C-32, 2, February 1983.
J. A. Feldman, F. M. Gaverick, F. M. Rhodes and J. R. Mann, “A wafer scale integration systolic processor for connected word recognition,” ICASSP ’84, IEEE, San Diego, March 1984.
H. T. Kung, “Systolic algorithms for the CMU warp processor,” Proceedings of the Seventh International Conference on Pattern Recognition, Quebec, Canada, July 1984.
D. H. D. Warren, “A view of the Fifth Generation and its impact,” The AI Magazine, Fall 82.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1985 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bisiani, R. (1985). Computer Systems for High-Performance Speech Recognition. In: De Mori, R., Suen, C.Y. (eds) New Systems and Architectures for Automatic Speech Recognition and Synthesis. NATO ASI Series, vol 16. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-82447-0_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-82447-0_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-82449-4
Online ISBN: 978-3-642-82447-0
eBook Packages: Springer Book Archive