Links Between Markov Models and Multilayer Perceptrons

  title={Links Between Markov Models and Multilayer Perceptrons},
  author={Herv{\'e} Bourlard and Christian Wellekens},
Hidden Markov models are widely used for automatic speech recognition. They inherently incorporate the sequential character of the speech signal and are statistically trained. However, the a-priori choice of the model topology limits their flexibility. Another drawback of these models is their weak discriminating power. Multilayer perceptrons are now promising tools in the connectionist approach for classification problems and have already been successfully tested on speech recognition problems… CONTINUE READING
Highly Influential
This paper has highly influenced 14 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS


Publications citing this paper.
Showing 1-10 of 173 extracted citations

Image Visual Realism: From Human Perception to Machine Computation

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2018
View 12 Excerpts
Highly Influenced

Acoustic Modeling With Hierarchical Reservoirs

IEEE Transactions on Audio, Speech, and Language Processing • 2013
View 4 Excerpts
Highly Influenced


Publications referenced by this paper.
Showing 1-10 of 13 references

Speech Pattern Discrimination and Multilayer Perceptrons

H. Bourlard, C. J. Wellekens
Computer, Speech and Language, • 1989
View 7 Excerpts
Highly Influenced

An introduction to computing with neural nets

IEEE ASSP Magazine • 1987
View 4 Excerpts
Highly Influenced

The Acoustic-Modeling Problem in A utomatic Speech Recognition, Ph.D. thesis, Comp.Sc.Dep

P. Brown
View 4 Excerpts
Highly Influenced

Maximum Mutual Information Estimation of Hidden Markov Model Parameters for Speech Recognition, Proc.ICASSP-86, Tokyo, ppA9-52

L. R. Bahl, P. F. Brown, P. V. de Souza, R. L. Mercer
View 4 Excerpts
Highly Influenced

Continuous speech recognition by statistical methods

Proceedings of the IEEE • 1976
View 5 Excerpts
Highly Influenced

Connectionist Learning Procedures

Artif. Intell. • 1989
View 2 Excerpts

Similar Papers

Loading similar papers…