Abstract
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.
Chapter PDF
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
L.R. Rabiner, Juang B.-H., and C.-H. Lee. An overview of automatic speech recognition. In Lee C.-H.,F.K. Soong, and K.K. Paliwal, editors, Automatic Speech and Speaker Recognition Advanced Topics. Kluwer, Boston, 1996.
P.C. Woodland, C.J. Leggetter, J.J. Odell, V. Valtchev, and S.J. Young. The 1994 HTK large vocabulary speech recognition system. In ICASSP’95, volume I, pages 73–76, 1995.
S. Glinski and D. Roe. Spoken language recognition on a DSP array processor. IEEE Transactions on Parallel and Distributed Systems, 5(7):697–703, July 1994.
R. Moore. Recogition-the stochastic modelling approach. In C. Rowden, editor, Speech Processing, pages 223–255. McGraw-Hill, London, 1993.
L.R. Rabiner. A tutorial on Hidden Markov Models and selected applications in speech recognition. Proceedings of the IEEE, 77:257–285, February 1989.
L.A. Liporace. Maximum likelihood estimation for multivariate observations of Markov sources. IEEE Transactions on Information Theory, 28(5):729–734, September 1982.
W. Turin. Unidirectional and parallel Baum-Welch algorithms. IEEE Transactions on Speech and Audio Processing, 6(6):516–523, November 1998.
S.K. Das and M.A. Picheny. Issues in practical large vocabulary isolated word recognition: The IBM Tangora system. In C-H. Lee, F.K. Soong, and K.K. Paliwal, editors, Automatic Speech and Speaker Recognition Advanced Topics, pages 457–479. Kluwer, Boston, 1996.
S. Baker. CORBA Distributed Objects Using Orbix. Addison-Wesley, Harlow, UK, 1997.
TakeFive Software GmbH, Stichting Mathematisch Centrum, Amsterdam, the Netherlands. SNiFF+ Release 2.2_User’s Guide and Reference, 1996.
G.V. Wilson and P. Lu, editors. Parallel Programming Using C++. MIT, Cambridge, MA, 1996.
B. Beck. Shared-memory parallel programming in C++. IEEE Software, 7(4): 38–48, July 1990.
Y. Wu and T.G. Lewis. Parallelism encapsulation in C++. In International Conference on Parallel Processing, volume II, pages 35–42. Pennsylvania State University, 1990.
G.D. Forney. The Viterbi algorithm. Proceedings of the IEEE, 61(3):268–278, March 1973.
R. Umbach and H. Ney. Improvements in beam search for 10; 000-word continuous-speech recognition. IEEE Transactions on Speech and Audio Processing, 2(2):353–356, April 1994.
S.P.A. Ringland. Application of grammar constraints to ASR using signature functions. In Speech Recognition and Coding, pages 260–263. Springer, Berlin, 1995. Volume 147 NATO ASI Series F.
S. Hovell. The incorporation of path merging in a dynamic network parser. In ESCA, EuroSpeech97, volume 1, pages 155–158, 1997.
S. Austin, R. Schwartz, and P. Placeway. The forward-backward search algorithm. In International Conference on Acoustics, Speech, and Signal Processing, volume 1, pages 697–700, 1991.
S. Young. A review of large-vocabulary continuous-speech recognition. IEEE Signal Processing Magazine, pages 45–57, September 1996.
D. Ollason, S. Hovell, and M. Wright. Requirements and design of the new continuous speech recognition parser-the Grid. Technical report, BT Laboratories, Martlesham Heath, Ipswich, IP5 3RE, UK, 1998.
S.S. Lumetta and D.E. Culler. Managing concurrent access for shared memory active messages. In IPPS/SPDP’98, 1998. 7 pages from http://now.CS.berkeley.EDU/Papers2.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fleury, M., Downton, A.C., Clark, A.F. (1999). Parallel Structure in an Integrated Speech-Recognition Network. In: Amestoy, P., et al. Euro-Par’99 Parallel Processing. Euro-Par 1999. Lecture Notes in Computer Science, vol 1685. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48311-X_138
Download citation
DOI: https://doi.org/10.1007/3-540-48311-X_138
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66443-7
Online ISBN: 978-3-540-48311-3
eBook Packages: Springer Book Archive