Progress in Broadcast News transcription at Dragon Systems

We report on progress in acoustic modelling and preprocessing in our Broadcast News transcription system. We have gone back to basics in acoustic modelling, and re-examined some of our standard practices, in particular the use of IMELDA and frequency warping, in the context of the Broadcast News corpus. We also report on some preliminary experiments with a generalization of IMELDA, “semi-tied covariances”. In combination, these improvements lead to a 3.5% absolute improvement over our eval97 models. We also describe our attempts to fix our rather primitive, silence-based preprocessing system, including initial results using a new speaker-change detection algorithm based on Hotelling´s T²-test