Abstract
As introduced in [4], Person-machine Communication (PMC) can be seen as an exchange of information coded in a way suitable for transmission through a physical medium. Coding is the process of producing a representation of what has to be communicated. The content to be communicated is structured using words represented by sequences of symbols of an alphabet and belonging to a given lexicon. Phrases are made by concatenating words according to the rules of a grammar and associated in order to be consistent with a given semantics. These various types of constraints are knowledge sources (KS) with which a symbolic version of the message to be exchanged is built. The symbolic version undergoes further transformations that make it transmittable trough a physical channel.
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
Anastasakos T., Mc Donough J. and Makhoul J. (1997) Speaker adaptive training: a maximum likelihood approach to speaker normalization.. In In Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing, Munich, germany, 1997, pp. 1043–1046.
Bahl L.R., Jelinek F.J. and Mercer R.L., A Maximum Likelihood Approach To Continuous Speech Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-5, no. 2, pp. 179–190, 1983.
Brugnara F; and de Mori R., Acoustic Modeling, chapter 5 of Renato De Mori Ed., SPOKEN DIALOGUES WITH COMPUTERS, Academic Press, 1998
De Mori R. Ed., SPOKEN DIALOGUES WITH COMPUTERS, Academic Press, 1998
Dugast C., Aubert X., Kneser R. (1995), The Philips Large-Vocabulary Recognition System for American English, French and German. Eurospeech, Madrid Spain pp
Federico M.,Cettolo M., Brugnara F., Antoniol G. (1995), Language Modeling for Efficient Beam-Search. Computer Speech and Language, 9: 353–379.
Gauvain J.L., and Lee C.H., Maximum a posterioriestimation for multivariate Gaussian mixture observations of markov Chains. IEEE Transactions on Speech and Audio Processing, vol. 2, pp. 291–298, 1994.
Jelinek F.J., STATISTICAL METHODS FOR SPEECH RECOGNITION, The MIT Press, 1997
Junqua J.C. and Haton J.P., ROBUSTNESS IN AUTOMATIC SPEECH RECOGNITION, Kluwer, 1996
Lee C.H., Soong F.K. and Paliwal K.K. Eds., AUTOMATIC SPEECH AND SPEAKER RECOGNITION: ADVANCED TOPICS. Kluewer 1996.
Leggeter C.J. and Woodland P.C., Maximum likelihood linear regression for speaker adaptation of continuos density hidden Markov models. Computer Speech and Language, vol. 9, pp. 171–185, 1995.
Lowerre B., A Comparative Performance Analysis Of Speech Understanding Systems. Ph. D. Thesis, Computer Science dept., Carnegie Mellon University, Pittsburgh, PA., 1976.
Ney H., Connected Utterance Recognition Using Dynamic Programming. Proc. 3rd FASE Conference, DAGA, Goettingen, Germany, pp. 1119–1125, 1992.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag London Limited
About this paper
Cite this paper
de Mori, R. (1999). Statistical Methods for Automatic Speech Recognition. In: Chollet, G., Di Benedetto, M.G., Esposito, A., Marinaro, M. (eds) Speech Processing, Recognition and Artificial Neural Networks. Springer, London. https://doi.org/10.1007/978-1-4471-0845-0_7
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0845-0_7
Publisher Name: Springer, London
Print ISBN: 978-1-85233-094-1
Online ISBN: 978-1-4471-0845-0
eBook Packages: Springer Book Archive