Conference paper
Large vocabulary natural language continuous speech recognition
L.R. Bahl, R. Bakis, et al.
ICASSP 1989
A general linear prediction framework is developed for the derivation of the complex split Levinson algorithm, which leads naturally to a structural interpretation of the redundancy present in the classical Levinson-Durbin algorithm. A novel order-recursive predictor structure is presented. It is conceptually simpler than a lattice realization since it propagates only one (generalized) prediction error. When the usual prediction error is desired, it can be recovered through a simple terminal stage.
L.R. Bahl, R. Bakis, et al.
ICASSP 1989
Eveline J. Bellegarda, Jerome R. Bellegarda, et al.
ICASSP 1995
Jerome R. Bellegarda, David Nahamoo
ICASSP 1989
Jerome R. Bellegarda, Peter V. de Souza, et al.
ICASSP 1993