Advertisement

Phoneme-Lattice to Phoneme-Sequence Matching Algorithm Based on Dynamic Programming

  • Ciro Gracia
  • Xavier Anguera
  • Jordi Luque
  • Ittai Artzi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8854)

Abstract

A novel phoneme-lattice to phoneme-sequence matching algorithm based on dynamic programming is presented in this paper. Phoneme lattices have been shown to be a good choice to encode in a compact way alternative decoding hypotheses from a speech recognition system. These are typically used for the spoken term detection and keyword-spotting tasks, where a phoneme sequence query is matched to a reference lattice. Most current approaches suffer from a lack of flexibility whenever a match allowing phoneme insertions, deletions and substitutions is to be found. We introduce a matching approach based on dynamic programming, originally proposed for Minimum Bayes decoding on speech recognition systems. The original algorithm is extended in several ways. First, a self-trained phoneme confusion matrix for phoneme comparison is applied as phoneme penalties. Also, posterior probabilities are computed per arc, instead of likelihoods and an acoustic matching distance is combined with the edit distance at every arc. Finally, total matching scores are normalized based on the length of the optimum alignment path. The resulting algorithm is compared to a state-of-the-art phoneme-lattice-to-string matching algorithm showing relative precision improvements over 20% relative on an isolated word retrieval task.

Keywords

phoneme lattice search keyword search speech recognition information retrieval 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Szöke, I., Schwarz, P., Matjka, P., Karafit, M.: Comparison of keyword spotting approaches for informal continuous speech. In: Proceedings Eurospeech (2005)Google Scholar
  2. 2.
    Young, S.J., Brown, M., Foote, J.T., Jones, G.J., Sparck Jones, K.: Acoustic indexing for multimedia retrieval and browsing. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1997, vol. 1, pp. 199–202. IEEE (1997)Google Scholar
  3. 3.
    Nambiar, U., Faruquie, T., Subramaniam, L.V., Negi, S., Ramakrishnan, G.: Discovering customer intent in real-time for streamlining service desk conversations. In: Proceedings of the 20th ACM International Conference on Information and Knowledge Management, CIKM 2011, pp. 1383–1388. ACM, New York (2011), http://doi.acm.org/10.1145/2063576.2063776 Google Scholar
  4. 4.
    Chelba, C., Acero, A.: Position specific posterior lattices for indexing speech. In: Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, ACL 2005, pp. 443–450. Association for Computational Linguistics, Stroudsburg (2005), http://dx.doi.org/10.3115/1219840.1219895 CrossRefGoogle Scholar
  5. 5.
    Foote, J.T., Faate, J.T., Brown, M., Jones, G., Young, S., Jones, K.S., Yaung, J.S.J.: Video mail retrieval by voice: Towards intelligent retrieval and browsing of multimedia documents (1995)Google Scholar
  6. 6.
    Foote, J.T., Jones, G.J.F., Jones, K.S., Young, S.J.: Talker-independent keyword spotting for information retrieval (1995)Google Scholar
  7. 7.
    James, D.A., Young, S.J.: A fast lattice-based approach to vocabulary independent wordspotting. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1994, vol. 1, pp. I–377. IEEE (1994)Google Scholar
  8. 8.
    Wilpon, J., Rabiner, L., Lee, C.-H., Goldman, E.: Automatic recognition of keywords in unconstrained speech using hidden markov models. IEEE Transactions on Acoustics, Speech and Signal Processing 38(11), 1870–1878 (1990)CrossRefGoogle Scholar
  9. 9.
    Knill, K.M., Young, S.: Fast implementation methods for viterbi-based word-spotting. In: Proc. ICASSP, pp. 522–525 (1996)Google Scholar
  10. 10.
    Price, P., Fisher, W., Bernstein, J., Pallett, D.: The darpa 1000-word resource management database for continuous speech recognition. In: International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1988, vol. 1, pp. 651–654 (April 1988)Google Scholar
  11. 11.
    Thambiratnam, K., Sridharan, S.: Dynamic match phone-lattice searches for very fast and accurate unrestricted vocabulary keyword spotting. In: Proc. ICASSP, vol. 5, pp. 465–468 (2005)Google Scholar
  12. 12.
    Young, S., Woodland, P.C., Byrne, W.J.: Htk version 3.4.1: User, reference and programmer manual (September 1993)Google Scholar
  13. 13.
    Audhkhasi, K., Verma, A.: Keyword search using modified minimum edit distance measure. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2007, vol. 4, pp. IV–929–IV–932 (April 2007)Google Scholar
  14. 14.
    Wang, D.: Out of vocabulary spoken term detection. PhD thesis, Institute for Communicating and Collaborative Systems, School of Informatics, University of Edinburgh (2010)Google Scholar
  15. 15.
    Xu, H., Povey, D., Mangu, L., Zhu, J.: Minimum bayes risk decoding and system combination based on a recursion for edit distance. Computer Speech and Language 25(4), 802–828 (2011), http://www.sciencedirect.com/science/article/pii/S0885230811000192 CrossRefGoogle Scholar
  16. 16.
    Carlin, M.A., Thomas, S., Jansen, A., Hermansky, H.: Rapid evaluation of speech representations for spoken term discovery. In: INTERSPEECH, pp. 821–824 (2011)Google Scholar
  17. 17.
    Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions and reversals. Soviet Physics Doklady 10, 707 (1966)MathSciNetGoogle Scholar
  18. 18.
    Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P., Silovsky, J., Stemmer, G., Vesely, K.: The kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding, vol. 2(2), pp. 2–3. IEEE Signal Processing Society (December 2011), iEEE Catalog No.: CFP11SRW-USBGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Ciro Gracia
    • 1
    • 2
  • Xavier Anguera
    • 1
  • Jordi Luque
    • 1
  • Ittai Artzi
    • 3
  1. 1.Telefonica Research, Edificio Telefonica-Diagonal 00BarcelonaSpain
  2. 2.Department of Information and Communications TechnologiesUniversitat Pompeu FabraBarcelonaSpain
  3. 3.Tel Aviv UniversityTel AvivIsrael

Personalised recommendations