Abstract
Automatic speech recognition has generally been treated as a problem of Bayesian classification. This is suboptimal when the distributions of the training data do not match those of the test data to be recognized. In this paper we propose an alternate analogous classification paradigm, in which classes are modeled by thermodynamic systems, and classification is performed through a minimum energy rule. Bayesian classification is shown to be a specific instance of this paradigm when the temperature of the systems is unity. Classification at elevated temperatures naturally provides a mechanism for dealing with statistical variations between test and training data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Singh, R., Raj, B., Virtanen, T.: The basics of automatic speech recognition. In: Techniques for Noise Robustness in Automatic Speech Recognition. John Wiley and Sons Inc. (2012)
Singh, R.: Audio classification with thermodynamic criteria. In: Proceedings IEEE International Workshop on Cloud Computing for Signal Processing, Coding and Networking (2014)
Singh, R., Kumatani, K.: Free energy for speech recognition. In: Proceedings International Conference Acoustics, Speech and Signal Processing (2015)
Landau, L.D., Lifshitz, E.M.: Statistical Physics: Course of Theoretical Physics, vol. 5, 3rd edn, p. 12. Pergamon Press, Oxford (1980)
Ranzato, M.A., Boureau, Y.L., Yann, L.C.: Sparse feature learning for deep belief networks. Proc. Adv. Neural Inf. Process. Syst. 21, 1185–1192 (2008)
Callen, H.B.: Thermodynamics and an Introduction to Thermostatistics. John Wiley and Sons Inc. (1985)
Baum, L.E., Petrie, T.: Statistical inference for probabilistic functions of finite state Markov chains. Ann. Math. Stat. 37(6), 1554–1563 (1966)
Huang, X., Acero, A., Hon, H.W.: Spoken Language Processing: A Guide to Theory, Algorithm, and System Development. Prentice Hall (2001)
Cieri, C., Miller, D., Walker, K.: The Fisher Corpus: A Resource for the Next Generations of Speech-to-Text. In: International Conference on Language Resources and Evaluation (2004)
Aarts, E., Korst, J.: Simulated Annealing and Boltzmann Machines. John Wiley and Sons Inc. (1988)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Singh, R. (2016). Minimizing Free Energy of Stochastic Functions of Markov Chains. In: Esposito, A., et al. Recent Advances in Nonlinear Speech Processing. Smart Innovation, Systems and Technologies, vol 48. Springer, Cham. https://doi.org/10.1007/978-3-319-28109-4_23
Download citation
DOI: https://doi.org/10.1007/978-3-319-28109-4_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-28107-0
Online ISBN: 978-3-319-28109-4
eBook Packages: EngineeringEngineering (R0)