This Article 
 Bibliographic References 
 Add to: 
Some Relations Among Stochastic Finite State Networks Used in Automatic Speech Recognition
July 1990 (vol. 12 no. 7)
pp. 691-695

In the literature on automatic speech recognition, the popular hidden Markov models (HMMs), left-to-right hidden Markov models (LRHMMs), Markov source models (MSMs), and stochastic regular grammars (SRGs) are often proposed as equivalent models. However, no formal relations seem to have been established among these models to date. A study of these relations within the framework of formal language theory is presented. The main conclusion is that not all of these models are equivalent, except certain types of hidden Markov models with observation probability distribution in the transitions, and stochastic regular grammar.

[1] L. Bahl, F. Jelinek, and R. Mercer, "A maximum likelihood approach to continuous speech recognition,"IEEE Trans. Parrern Anal. Machine Intell., vol. PAMI-5, no. 2, pp. 179-190, 1983.
[2] F. Jelinek, "Continuous speech recognition by statistical methods,"Proc. IEEE, vol. 64, no. 4, pp. 532-556, 1976.
[3] L. R. Rabiner and B. H. Juang, "An introduction to hidden Markov models,"IEEE ASSP Mag., pp. 4-16, Jun. 1986.
[4] J. Baker, "The Dragon system-An overview,"IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-23, no. 1, pp. 24-29, 1975.
[5] L. Rabiner, S. Levinson, and M. Sondhi, "On the application of vector quantification and HMM's to speaker independent, isolated word recognition,"Bell Syst. Tech. J., vol. 62, no. 4, pp. 1075-1105, 1983.
[6] S. Levinson, L. Rabiner, and M. Sondhi, "An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition,"Bell Syst. Tech. J., vol. 62, no. 4, pp. 1035-1074, 1983.
[7] S. Levinson, "Structural methods in automatic speech recognition,"Proc. IEEE, vol. 73, no. 11, pp. 1625-1650, 1985.
[8] L. Rabiner, "Mathematical foundations of hidden Markov models," inRecent Advances in Automatic Speech Understanding and Dialog, H. Niemann, Ed. (NATO ASI Series). New York: Springer, 1988.
[9] A. Salomaa,Formal Languages. New York: Academic, 1973.
[10] R. Kashyap, "Syntactic decision rules for recognition of spoken words and phrases using stochastic automaton,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-1, no. 2, pp. 154-163, 1979.
[11] R. Schwarthet al., "Acoustic-phonetic decoding of speech," inRecent Advances in Speech Understanding and Dialog Systems, H. Niemann, Ed. New York: Springer, 1988.
[12] H. Cerf-Danonet al., "Speech recognition experiments with 10000 word dictionary, " inPattern Recognition and Applications, P. Devijver and J. Kittler, Eds. New York: Springer, 1987.
[13] K. Fu,Syntactic Pattern Recognition and Applications. Englewood Cliffs, NJ: Prentice-Hall, 1982.
[14] R. Gonzalez and M. Thomason,Syntactic Pattern Recognition: An Introduction. Reading, MA: Addison-Wesley, 1978.
[15] L. Miclet,Structural Methods in Pattern Recognition. North Oxford Academic, 1986.
[16] N. Abramson,Information Theory and Coding. New York: MCGraw-Hill, 1966.
[17] C. S. Wetherell, "Probabilistic languages: A review and some open questions,"Comput. Surveys, vol. 12, pp. 361-379, 1980.
[18] H. Rulot and E. Vidal, "An efficient algorithm for the inference of circuit-free automata, " inProc. NATO Advanced Research Workshop Syntactic Pattern Recognition, Ferrateet al., Eds. New York: Springer, 1988.
[19] S. Levinson, "A unified theory of composite pattern analysis for automatic speech recognition," inComputer Speech Processing, F. Fallside and W. Woods, Eds. Englewood Cliffs, NJ: Prentice-Hall, 1985.
[20] S. Levinson, "Some experiments with a linguistic processor for continuous speech recognition,"IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-31, no. 6, pp. 1549-1556, 1983.
[21] A. M. Derouault and B. Mérialdo, "Natural language modeling for phoneme-to-text transcription,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-8, no. 6, pp. 742-749, 1986.
[22] S. Nakagawa and M. Jilan, "Syllable-based connected spoken word recognition by two passO(n)DP matching and hidden Markov model, " inProc. ICASSP86, 1986, pp. 21.14.1-21.14.4.
[23] B. Merialdo, "Phonetic recognition using HMM's and maximum mutual information training, " inProc. ICASSP88, 1988, pp. 111-114.
[24] P. F. Brown, "The acoustic-modeling problem in automatic speech recognition," IBM Res. Center, Yorktown Heights, NY, Res. Rep. RC-12750, May 1987.
[25] E. S. Santos, "Realizations of fuzzy languages by probabilistic maxproduct and max-min automata," Inform. Sci., vol. 8, pp. 39-53, 1975.
[26] K. F. Lee, "Large-vocabulary speaker-independent continuous speech recognition: The SPHNIX systems," Carnegie-Mellon Univ., Tech. Rep. CMU-CS-88-148, 1988.

Index Terms:
stochastic finite state networks; automatic speech recognition; formal language theory; hidden Markov models; observation probability distribution; stochastic regular grammar; formal languages; grammars; Markov processes; speech recognition; stochastic processes
F. Casacuberta, "Some Relations Among Stochastic Finite State Networks Used in Automatic Speech Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 7, pp. 691-695, July 1990, doi:10.1109/34.56212
Usage of this product signifies your acceptance of the Terms of Use.