Use of a novel generalized fuzzy hidden Markov model for speech recognition

Author

Cheok, Adrian David ; Chevalier, Sylvain ; Kaynak, Mustafa ; Sengupta, Kuntal ; Chung, KO Chi

Author_Institution

Nat. Univ. of Singapore, Singapore

Volume

3

fYear

2001

fDate

6/23/1905 12:00:00 AM

Firstpage

1207

Lastpage

1210

Abstract

We discuss a type of hidden Markov model (HMM) based on fuzzy sets and fuzzy integral theory which generalizes the classical stochastic HMM. The Choquet integral is used as a fuzzy integral which relaxes one of the two independence assumptions that we had with the classical HMM. We apply this new model to speech recognition and compare the performance with the classical HMM. In this research, the main innovation is that this new generalized fuzzy HMM is applied for the first time to speech recognition. Due to the fuzziness of the model, an interesting gain can be observed in terms of a lower computation time

Keywords

fuzzy set theory; hidden Markov models; integral equations; probability; speech recognition; Choquet integral; computation time; fuzzy integral; fuzzy integral theory; fuzzy sets; generalized fuzzy hidden Markov model; independence assumptions; speech recognition; Fuzzy logic; Fuzzy sets; Hidden Markov models; Neural networks; Particle measurements; Robustness; Search problems; Speech recognition; Stochastic processes; Technological innovation;

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Systems, 2001. The 10th IEEE International Conference on

Conference_Location

Melbourne, Vic.

Print_ISBN

0-7803-7293-X

Type

conf

DOI

10.1109/FUZZ.2001.1008874

Filename

1008874