Scheduled System Maintenance:
Some services will be unavailable Sunday, March 29th through Monday, March 30th. We apologize for the inconvenience.
By Topic

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

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.
3 Author(s)
Hsiao, R. ; Language Technol. Inst., Carnegie Mellon Univ., Pittsburgh, PA ; Yik-Cheung Tam ; Schultz, T.

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).

Published in:

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

Date of Conference:

19-24 April 2009