Computer systems for high-performance speech recognition

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.

[1]  Kemal Oflazer,et al.  Partitioning in parallel processing of production systems , 1987 .

[2]  Salvatore J. Stolfo,et al.  Architecture and Applications of DADO: A Large-Scale Parallel Computer for Artificial Intelligence , 1983, IJCAI.

[3]  R. Bisiani,et al.  Task-oriented architectures , 1983, Proceedings of the IEEE.

[4]  Bruce T. Lowerre,et al.  The HARPY speech recognition system , 1976 .

[5]  W. Daniel Hillis,et al.  The connection machine , 1985 .

[6]  Richard James Swan.  The switching structure and addressing architecture of an extensible multiprocessor: cm*. , 1978 .

[7]  Pietro Laface,et al.  Parallel Algorithms for Syllable Recognition in Continuous Speech , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Ralph Grishman,et al.  The NYU Ultracomputer—Designing an MIMD Shared Memory Parallel Computer , 1983, IEEE Transactions on Computers.

[9]  James Holmes,et al.  The JSRU channel vocoder , 1980 .

[10]  Roberto Bisiani,et al.  A family of custom VLSI circuits for speech recognition , 1984, ICASSP.

[11]  Arvind,et al.  A critique of multiprocessing von Neumann style , 1983, ISCA '83.

[12]  Geoffrey E. Hinton,et al.  Massively Parallel Architectures for AI: NETL, Thistle, and Boltzmann Machines , 1983, AAAI.

[13]  Peter Neil Oleinick,et al.  The implementation and evaluation of parallel algorithms on c.mmp. , 1979 .

[14]  J. Makhoul,et al.  Linear prediction: A tutorial review , 1975, Proceedings of the IEEE.

[15]  Patrice Frison,et al.  A VLSI parallel machine for speech recognition , 1984, ICASSP.

[16]  Ronald A. Cole,et al.  Feature-based speaker-independent recognition of isolated english letters , 1983, ICASSP.

[17]  Scott E. Fahlman,et al.  NETL: A System for Representing and Using Real-World Knowledge , 1979, CL.

[18]  Richard D. Greenblatt,et al.  A LISP Machine , 1980, CAW '80.

[19]  R.W. Brodersen,et al.  A Switched-Capacitor Adaptive Lattice Filter , 1983, IEEE Journal of Solid-State Circuits.

[20]  Robert W. Brodersen,et al.  A dynamic time warp IC for a one thousand word recognition system , 1984, ICASSP.

[21]  Anoop Gupta,et al.  Measurements on production systems , 1983 .

[22]  Steven L. Garverick,et al.  A wafer scale integration systolic processor for connected word recognition , 1984, ICASSP.

[23]  Michael Picheny,et al.  Some experiments with large-vocabulary isolated-word sentence recognition , 1984, ICASSP.

[24]  Harold Boley,et al.  A preliminary survey of artificial intelligence machines , 1980, SGAR.

[25]  H. T. Kung.  Systolic algorithms for the CMU warp processor , 1984 .

[26]  Aaron E. Rosenberg,et al.  Considerations in dynamic time warping algorithms for discrete word recognition , 1978 .

[27]  Gary E. Kopec.  The integrated signal processing system ISP , 1984, ICASSP.

[28]  David W. Shipman.  SpireX: Statistical analysis in the spire acoustic-phonetic workstation , 1983, ICASSP.

[29]  Victor R. Lesser,et al.  The Hearsay-II Speech-Understanding System: Integrating Knowledge to Resolve Uncertainty , 1980, CSUR.

[30]  David H. D. Warren.  A View of the Fifth Generation and Its Impact , 1982, AI Mag..