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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Szöke, I., Schwarz, P., Matjka, P., Karafit, M.: Comparison of keyword spotting approaches for informal continuous speech. In: Proceedings Eurospeech (2005)
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)
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
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
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)
Foote, J.T., Jones, G.J.F., Jones, K.S., Young, S.J.: Talker-independent keyword spotting for information retrieval (1995)
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)
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)
Knill, K.M., Young, S.: Fast implementation methods for viterbi-based word-spotting. In: Proc. ICASSP, pp. 522–525 (1996)
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)
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)
Young, S., Woodland, P.C., Byrne, W.J.: Htk version 3.4.1: User, reference and programmer manual (September 1993)
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)
Wang, D.: Out of vocabulary spoken term detection. PhD thesis, Institute for Communicating and Collaborative Systems, School of Informatics, University of Edinburgh (2010)
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
Carlin, M.A., Thomas, S., Jansen, A., Hermansky, H.: Rapid evaluation of speech representations for spoken term discovery. In: INTERSPEECH, pp. 821–824 (2011)
Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions and reversals. Soviet Physics Doklady 10, 707 (1966)
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-USB
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Gracia, C., Anguera, X., Luque, J., Artzi, I. (2014). Phoneme-Lattice to Phoneme-Sequence Matching Algorithm Based on Dynamic Programming. In: Navarro Mesa, J.L., et al. Advances in Speech and Language Technologies for Iberian Languages. Lecture Notes in Computer Science(), vol 8854. Springer, Cham. https://doi.org/10.1007/978-3-319-13623-3_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-13623-3_11
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-13622-6
Online ISBN: 978-3-319-13623-3
eBook Packages: Computer ScienceComputer Science (R0)