Discriminative coding with predictive neural networks

摘要

In this paper, we present a new speech coding named NPC (Neural Predictive Coding) based on an original neural predictive structure. The system is designed to predict the samples of a speech signal window from previous ones. The goal of thiscoding is to extract the signal discriminative features relative to the database which it is extracted. After a precise description of NPC coding, we discuss about the first phase of the algorithm: the adjustment of the parameters of the coder. Wepresent experiences which show an improvement on telephone speech recognition compared with LPC. The signal windows are extracted from the telephone speech signal database NTIMIT.