Maximum mutual information estimation of HMM parameters for continuous speech recognition using the N-best algorithm

Author

Chow, Yen-Lu

Author_Institution

BBN Syst. & Technol. Corp., Cambridge, MA, USA

fYear

1990

fDate

3-6 Apr 1990

Firstpage

701

Abstract

An application of discriminative training methods, maximum mutual information (MMI) training, to large-vocabulary continuous speech recognition is described. An algorithm is developed for efficient MMI estimation of HMM parameters, including exponential codebook coefficients, which cannot be estimated using maximum likelihood (ML) methods. Continuous speech recognition performance of the BYBLOS system on the DARPA 1000-word resource management speech corpus is presented

Keywords

Markov processes; learning systems; parameter estimation; probability; speech recognition; BYBLOS system; DARPA; continuous speech recognition; discriminative training methods; exponential codebook coefficients; hidden Markov model; learning systems; maximum mutual information training; parameter estimation; resource management speech corpus; Hidden Markov models; Management training; Maximum likelihood decoding; Maximum likelihood estimation; Mutual information; Natural languages; Parameter estimation; Resource management; Speech recognition; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on

Conference_Location

Albuquerque, NM

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1990.115863

Filename

115863