A neural network based, speaker independent, large vocabulary, continuous speech recognition system: the WERNICKE project

Abstract

This paper describes the research underway for the ES-PRIT WERNICKE project. The project brings together a n umber of di erent groups from Europe and the US and focuses on extending the state-of-the-art for hybrid hidden Markov model/connectionist approaches to large vocabulary, continuous speech recognition. This paper describes the speci c goals of the research and presents the work performed to date. Results are reported for the resource management t a l k er-independent recognition task. The paper concludes with a discussion of the projected future work.