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

Joseph Di Martino (1) , Jean-François Mari (1) , B. Mathieu , K. Perot , Kamel Smaïli (1)

1 PAROLE - Analysis, perception and recognition of speech

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

Mots clés: Hidden Markov Model; Finite state automata

Domaines: Intelligence artificielle [cs.AI]

Joseph Di Martino, Jean-François Mari, B. Mathieu, K. Perot, Kamel Smaïli. Which model for future speech recognition systems: Hidden Markov models for finite-state automata?. IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP-94, 1994, Adelaïd, Australia. pp.633-635. ⟨hal-00589127⟩