论文信息 - Which model for future speech recognition systems: hidden Markov models or finite-state automata?

Which model for future speech recognition systems: hidden Markov models or finite-state automata?

Representation of speech using hidden Markov models is compared with a representation based on finite-state automata. Experimental results are presented for both methods and the respective advantages and disadvantages discussed.<<ETX>>

Jean-François Mari | Kamel Smaïli | Bruno Mathieu | Joseph Di Martino | Karine Perot

[1] Stephen E. Levinson,et al. Speaker independent isolated digit recognition using hidden Markov models , 1982, ICASSP.

[2] Lalit R. Bahl,et al. A new algorithm for the estimation of hidden Markov model parameters , 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

[3] L. Baum,et al. An inequality and associated maximization technique in statistical estimation of probabilistic functions of a Markov process , 1972 .

[4] Marc Blanchet,et al. An algorithm for the dynamic inference of hidden Markov models (DIHMM) , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5] L. R. Rabiner,et al. Recognition of isolated digits using hidden Markov models with continuous mixture densities , 1985, AT&T Technical Journal.