'Blade Runner': A real-time speech recognizer

A real-time prototype speech recognizer has been implemented on a 66-processor distributed-memory parallel computer. Simple phrases are recognized in approximately 4 to 10 seconds. Scalability, performance and flexibility are the three main aims of this implementation, the ultimate goal being to construct a large vocabulary speech recognizer which responds quickly. A set of three techniques is investigated in this implementation: asynchronous methodology to minimize synchronization overheads, distributed control to avoid a central communications bottleneck, and dynamic load balancing to provide a flexible response to an unpredictable computational load. The effect on memory, processor time allocation and communications is observed in real-time using hardware monitoring aids.

[1]  Ltd Corporated Inmos.  Transputer development system , 1988 .

[2]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[3]  Edsger W. Dijkstra,et al.  Termination Detection for Diffusing Computations , 1980, Inf. Process. Lett..

[4]  L. Rabiner,et al.  An introduction to hidden Markov models , 1986, IEEE ASSP Magazine.

[5]  Henry F. Korth.  Deadlock freedom using edge locks , 1982, TODS.

[6]  DAVID GELERNTER.  A DAG-Based Algorithm for Prevention of Store-and-Forward Deadlock in Packet Networks , 1981, IEEE Transactions on Computers.

[7]  C. A. R. Hoare,et al.  Communicating sequential processes , 1978, CACM.

[8]  Prathima Agrawal,et al.  Connected speech recognition on a multiple processor pipeline , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

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

[10]  Anne Greenbaum.  Synchronization costs on multiprocessors , 1989, Parallel Comput..

[11]  N. T. Condick,et al.  A transputer based speech recognition system , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[12]  David May,et al.  A Tutorial Introduction To Occam Programming , 1987 .

[13]  Geoffrey C. Fox.  Parallel Computing Comes of Age: Supercomputer Level Parallel Computations at Caltech , 1989, Concurr. Pract. Exp..

[14]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[15]  S. Miki,et al.  Speaker-independent isolated-word recognition LSI , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[16]  Timothy S. Axelrod,et al.  Effects of synchronization barriers on multiprocessor performance , 1986, Parallel Comput..

[17]  Murray Hill,et al.  Yacc: Yet Another Compiler-Compiler , 1978 .

[18]  Kai-Fu Lee,et al.  Automatic Speech Recognition , 1989 .