Empirical Assessment of Two Strategies for Optimizing the Viterbi Algorithm

  • Roberto Esposito
  • Daniele P. Radicioni
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5883)


The Viterbi algorithm is widely used to evaluate sequential classifiers. Unfortunately, depending on the number of labels involved, its time complexity can still be too high for practical purposes. In this paper, we empirically compare two approaches to the optimization of the Viterbi algorithm: Viterbi Beam Search and CarpeDiem. The algorithms are illustrated and tested on datasets representative of a wide range of experimental conditions. Results are reported and the conditions favourable to the characteristics of each approach are discussed.


Beam Size Viterbi Algorithm Markov Assumption Continuous Speech Recognition Perceptron Algorithm 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Viterbi, A.J.: Error Bounds for Convolutional Codes and an Asymptotically Optimum Decoding Algorithm. IEEE Transaction on Information Theory 13, 260–269 (1967)zbMATHCrossRefGoogle Scholar
  2. 2.
    Felzenszwalb, P.F., Huttenlocher, D.P., Kleinberg, J.M.: Fast Algorithms for Large-State-Space HMMs with Applications to Web Usage Analysis. In: Advances in Neural Information Processing Systems (2003)Google Scholar
  3. 3.
    Siddiqi, S.M., Moore, A.W.: Fast Inference and Learning in Large-State-Space HMMs. In: Proceedings of the 22nd International Conference on Machine Learning (2005)Google Scholar
  4. 4.
    Dietterich, T.G., Domingos, P., Getoor, L., Muggleton, S., Tadepalli, P.: Structured machine learning: the next ten years. Machine Learning 73(1), 3–23 (2008)CrossRefGoogle Scholar
  5. 5.
    Lowerre, B., Reddy, R.: The Harpy Speech Understanding System. In: Trends in Speech Recognition, pp. 340–360. Prentice-Hall, Englewood Cliffs (1980)Google Scholar
  6. 6.
    Ney, H., Haeb-Umbach, R., Tran, B., Oerder, M.: Improvements in beam search for 10000-word continuous speech recognition. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 1, pp. 9–12 (1992)Google Scholar
  7. 7.
    Collins, M., Roark, B.: Incremental parsing with the perceptron algorithm. In: Proceedings of the Association for Computational Linguistics, pp. 111–118 (2004)Google Scholar
  8. 8.
    Esposito, R., Radicioni, D.P.: CarpeDiem: an Algorithm for the Fast Evaluation of SSL Classifiers. In: Proceedings of the 24th Annual International Conference on Machine Learning, ICML 2007 (2007)Google Scholar
  9. 9.
    Spohrer, J.C., Brown, P.F., Hochschild, P.H., Baker, J.K.: Partial traceback in continuous speech recognition. In: Proc. IEEE Int Cong. Cybernetics and Societ, Boston, MA (1980)Google Scholar
  10. 10.
    Bridle, J.S., Brown, M.D., Chamberlain, R.M.: An algorithm for connected word recognition. In: Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP 1982, pp. 899–902 (1982)Google Scholar
  11. 11.
    Ney, H., Mergel, D., Noll, A., Paeseler, A.: Data driven search organization for continuous speech recognition. IEEE Transactions on Signal Processing 40, 272–281 (1987)CrossRefGoogle Scholar
  12. 12.
    Xu, Y., Fern, A.: On learning linear ranking functions for beam search. In: Ghahramani, Z. (ed.) Proceedings of the 24th International Conference on Machine Learning, pp. 1047–1054 (2007)Google Scholar
  13. 13.
    Collins, M.: Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Roberto Esposito
    • 1
  • Daniele P. Radicioni
    • 1
  1. 1.Dipartimento di InformaticaUniversità di Torino 

Personalised recommendations