Third International Conference on Spoken Language Processing (ICSLP 94) Yokohama, Japan September 18-22, 1994

Minimum-Error-Rate Training of Predictive Neural Network Models

KyungMin Na, JaeYeol Rheem, SouGuil Ann

Dept. of Electronics Engineering, Seoul National University, Seoul, Korea

Recently, predictive neural network models (PNNM) have proven successful in various speech recognition tasks. But, they suffer from poor discrimination for acoustically similar speech signals. In this paper, a new discriminative training algorithm based on the minimum-error-rate decision rule is proposed. Experiments on the Korean digits recognition have shown 37.5 % reduction of the number of recognition errors.

Full Paper

Bibliographic reference.  Na, KyungMin / Rheem, JaeYeol / Ann, SouGuil (1994): "Minimum-error-rate training of predictive neural network models", In ICSLP-1994, 1479-1482.