Acoustic-phonetic decoding using a transition controlled neural net

An artificial neural network (ANN) architecture for modeling the transitions between consecutive phones is presented. These `phone transition´ models are particularly suited for taking into account the coarticulation phenomena in continuous speech. In order to obtain robust and generalizing probability estimates, the evidences of variable frame rate-based transition models and those of context-independent segment-based phone models are combined by means of an additional ANN, called the transition controlled neural network (TCNN). The concept of the transition approach was introduced in Verhasselt and Martens (1994); in the present paper a new and more sophisticated implementation is proposed and evaluated on a phone recognition task. The new TCNN-approach significantly outperforms the old one