Parallel Structure in an Integrated Speech-Recognition Network

Large-vocabulary continuous-speech recognition (LVCR) speaker-independent systems which integrate cross-word context dependent acoustic models and n-gram language models are difficult to parallelize because of their interwoven structure, large dynamic data structures, and complex object-oriented software design. This paper shows how retrospective decomposition can be achieved if a quantitative analysis is made of dynamic system behaviour. A design which accommodates unforeseen effects and future modifications is presented.

[1]  Louis A. Liporace,et al.  Maximum likelihood estimation for multivariate observations of Markov sources , 1982, IEEE Trans. Inf. Theory.

[2]  H. Ney,et al.  Improvements in beam search for 10000-word continuous speech recognition , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  Steve Austin,et al.  The forward-backward search algorithm , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[4]  Biing-Hwang Juang,et al.  An Overview of Automatic Speech Recognition , 1996 .

[5]  Seán Baker.  CORBA distributed objects - using ORBIX , 1997 .

[6]  Steve Young,et al.  A review of large-vocabulary continuous-speech , 1996, IEEE Signal Process. Mag..

[7]  Jr. G. Forney,et al.  The viterbi algorithm , 1973 .

[8]  Simon Hovell.  The incorporation of path merging in a dynamic network recogniser , 1997, EUROSPEECH.

[9]  David E. Culler,et al.  Managing concurrent access for shared memory active messages , 1998, Proceedings of the First Merged International Parallel Processing Symposium and Symposium on Parallel and Distributed Processing.

[10]  Kuldip K. Paliwal,et al.  Automatic Speech and Speaker Recognition: Advanced Topics , 1999 .

[11]  P.C. Woodland,et al.  The 1994 HTK large vocabulary speech recognition system , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[12]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[13]  Stephen C. Glinski,et al.  Spoken Language Recognition on a DSP Array Processor , 1994, IEEE Trans. Parallel Distributed Syst..

[14]  Steve Young,et al.  A review of large-vocabulary continuous-speech recognition , 1996 .

[15]  Gregory V. Wilson,et al.  Parallel Programming Using C , 1996 .

[16]  Ted G. Lewis,et al.  Parallelism Encapsulation in C++ , 1990, ICPP.

[17]  Bob Beck,et al.  Shared-memory parallel programming in C++ , 1990, IEEE Software.

[18]  William Turin,et al.  Unidirectional and parallel Baum-Welch algorithms , 1998, IEEE Trans. Speech Audio Process..

[19]  Simon P. A. Ringland.  Application of Grammar Constraints to ASR Using Signature Functions , 1995 .

[20]  Donald G. Childers,et al.  Speech Processing , 1999 .

[21]  S. K. Das,et al.  Issues in Practical Large Vocabulary Isolated Word Recognition: The IBM Tangora System , 1996 .

[22]  Antonio José Rubio Ayuso,et al.  Speech Recognition and Coding , 1995 .