Abstract
Decoding or searching is an important task in both speaker and speech recognition. In speaker verification (SV), given a spoken password and a speakerdependent hidden Markov model (HMM), the task of decoding or searching is to find optimal state alignments in the sense of maximum likelihood score of the entire utterance. Currently, the most popular decoding algorithm is the Viterbi algorithm with a pre-defined beam width to reduce the search space; however, it is difficult to determine a suitable beam width beforehand. A small beam width may miss the optimal path while a large one may slow down the process. To address the problem, the author has developed a non-heuristic algorithm to reduce the search space. The details are presented in this chapter.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bahl L. R. et al.: “Large vocabulary natural language continuous speech recognition”, in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, pp. 465–467, May 1989
Bansal R. K.: “An algorithm for detecting a change in stochastic process”, Master Thesis, University of Connecticut, EECS Dept., 1983
Bansal, R. K., Papantoni-Kazakos, P.: “An algorithm for detecting a change in stochastic process”. IEEE Trans. Information Theory IT-32, 227–235 (1986)
Bellman, R. E.: Dynamic Programming. Princeton University Press, Princeton (1957)
Brodsky, B., Darkhovsky, B. S.: Nonparametric methods in change-point problems. Kluwer Academic, Boston (1993)
Chen, J. K., Soong, F. K.: “An n-best candidates-based discriminative training for speech-recognition applications”. IEEE Trans. on Speech and Audio Processing 2, 206–216 (1994)
Deller, J. R., Proakis, J. G., Hansen, J. H. L.: Discrete-time processing of speech signals. Macmillan Publishing, NY (1993)
Deshmukh, N., Ganapathiraju, A., Picone, J.: search for large-vocabulary conversational speech recognition”. IEEE Signal Processing Magazine 16, 84–107 (1999)
Forney, G. D.: “The Viterbi algorithm”. Proceeding of IEEE 61, 268–278 (1973)
Kazakos, D., Papantoni-Kazakos, P.: Detection and Estimation. Computer Science Press, NY (1990)
Lee, C.-H., Rabiner, L. R.: “A frame-synchronous network search algorithm for connected word recognition”. IEEE Transactions on Acoustics, Speech, and Signal Processing 37, 1649–1658 (1989)
Li, Q.: “A detection approach to search-space reduction for HMM state alignment in speaker verification”. IEEE Trans. on Speech and Audio Processing 9, 569–578 (2001)
Li Q.: “A fast decoding algorithm based on sequential detection of the changes in distribution”. in Proc. Int’l Conf. on Spoken Language Processing (Sydney), Nov. 1998
Li Q.: “A fast, sequential decoding algorithm with application to speaker verification”. in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (Phoenix), March 1999
Li Q., Juang B.-H.: “Speaker verification using verbal information verification for automatic enrollment”. in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (Seattle), May 1998
Lorden, G.: “Procedures for reacting to a change in distribution”. The Annals of Mathematical Statistics 42, 1897–1908 (1971)
Lowerre, B., Reddy, R.: The HARPY speech understanding system, In: Lea, W. A. (ed) Trends in Speech Recognition., Printice Hall, NJ (1980)
Ney H., Haeb-Umbach R., Tran B.-H., Oerder M. “Improvements in beam search for 10000-word continuous speech recognition”. in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (San Francisco, CA), pp. I-9–I-12, March 1992
Ney, H., Ortmanns, S.: “Dynamic programming search for continuous speech recognition”. IEEE Signal Processing Magazine 16, 64–83 (1999)
Nguyen L., Schwartz R., Kubala F., Placeway P.: “Search algorithms for software-only real-time recognition with very large vocabularies”. in Proceedings of DARPA Human language Technology Workshop, pp. 91–95, March 1993
Page, E. S.: “Continuous inspection schemes”. Biometrika 41, 100–115 (1954)
Page, E. S.: “A test for a change in a parameter occuring at an unknown point”. Biometrika 42, 523–527 (1955)
Papoulis, A.: Probability, Random variables, and stochastic processes. McGraw-Hill, NY (1984)
Parthasarathy S., Rosenberg A. E.: “General phrase speaker verification using sub-word background models and likelihood-ratio scoring”. in Proceedings of ICSLP-96 (Philadelphia), October 1996
Rosenberg A. E., Parthasarathy S. “Speaker background models for connected digit password speaker verification”. in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (Atlanta), pp. 81–84, May 1996
Viterbi, A. J.: “Error bounds for convolutional codes and an asymptotically optimal decoding algorithm”. IEEE Transactions on Information Theory IT-13, 260–269 (1967)
Wald, A.: Sequential analysis. Chapman & Hall, NY (1947)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Li, Q.(. (2012). Detection-Based Decoder. In: Speaker Authentication. Signals and Communication Technology. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23731-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-23731-7_6
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23730-0
Online ISBN: 978-3-642-23731-7
eBook Packages: EngineeringEngineering (R0)