Speech recognition method using quantised LSP parameters in CELP-type coders

Abstract

A low-complexity speech recognition method applicable to digital communication networks is proposed. A feature set suitable for speech recognition is obtained from quantised LSP parameters in CELP-type coders without reconstructing the speech signals. The authors present the effects of the speech coder on speaker-independent recognition performance. and show that the recognition accuracy of the proposed method is better than that of the recogniser using reconstructed speech signals.