Large vocabulary continuous speech recognition of Wall Street Journal data

Abstract

The authors report on the progress that has been made at Dragon Systems in speaker-independent large-vocabulary speech recognition using speech from DARPA's Wall Street Journal corpus. First they present an overview of the recognition and training algorithms. Then, they describe experiments involving two improvements to these algorithms, moving to higher-dimensional streams and using an IMELDA transformation. They also present some results showing the reduction in error rates.< <ETX>&gt;</ETX>