Key points are not available for this paper at this time.
The paper contains a description of the Philips#RWTH 1998 HUB4 system which was build in a joint e#ort of Philips Research Laboratories Aachen and Aachen University of Technology. We will focus our discussion on recent improvements compared to the original 1997 HUB4 system #Beyerlein + 1998# and evaluate them on the HUB497 evaluation data. The paper will deal with 1. a rough system overview, including slight modi#cations in feature extraction, training and recognition 2. improvements obtained in audio stream segmentation and segment clustering, 3. log-linear interpolation of #distance language models, 4. and the integration of various acoustic and language models via Discriminative Model Combination #DMC#. The performance of the described system is 23# #relative# better than the performance of the 1997 Philips HUB4 system. Aword error rate of 17.9# was achieved on the 1997 HUB4 evaluation set, compared to 23.5# using the original 1997 system. 1. System Overview 1.1. Feature E...
Beyerlein et al. (Sun,) studied this question.