Generalized Baum-Welch algorithm for discriminative training on large vocabulary continuous speech recognition system

Author

Hsiao, Roger ; Tam, Yik-Cheung ; Schultz, Tanja

Author_Institution

Language Technol. Inst., Carnegie Mellon Univ., Pittsburgh, PA

fYear

2009

fDate

19-24 April 2009

Firstpage

3769

Lastpage

3772

Abstract

We propose a new optimization algorithm called Generalized Baum Welch (GBW) algorithm for discriminative training on hidden Markov model (HMM). GBW is based on Lagrange relaxation on a transformed optimization problem. We show that both Baum-Welch (BW) algorithm for ML estimate of HMM parameters, and the popular extended Baum-Welch (EBW) algorithm for discriminative training are special cases of GBW.We compare the performance of GBW and EBW for Farsi large vocabulary continuous speech recognition (LVCSR).

Keywords

hidden Markov models; maximum likelihood estimation; optimisation; speech recognition; vocabulary; Lagrange relaxation algorithm; ML estimation; discriminative training; generalized Baum-Welch algorithm; hidden Markov model; large vocabulary continuous speech recognition system; maximum likelihood estimation; optimization algorithm; Hidden Markov models; Lagrangian functions; Large-scale systems; Lattices; Maximum likelihood estimation; Mutual information; Natural languages; Parameter estimation; Speech recognition; Vocabulary; Speech recognition; discriminative training;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on

Conference_Location

Taipei

ISSN

1520-6149

Print_ISBN

978-1-4244-2353-8

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2009.4960447

Filename

4960447