IBM's LVCSR system for transcription of broadcast news used in the 1997 hub4 english evaluation
S Chen, Mark Gales, PS Gopalakrishnan, RA Gopinath, D Kavensky, Peder A. Olsen, Lazaros Polymenakos · Cambridge University Engineering Department Publications Database · 1998
This paper describes IBM’s large vocabulary continuous speech recognition (LVCSR) system used in the 1997 Hub4 English evaluation. It focusses on extensions and improvements to the system used in the 1996 evaluation. The recognizer uses an additional 35 hours of training data over the one used in the 1996 Hub4 evaluation [8]. It includes a number of new features: optimal feature space for acoustic modeling (in training and/or testing), filler-word modeling, Bayesian Information Criterion (BIC) based segmentation and segment clustering, an improved implementation of iterative MLLR, variance adaptation, and 4-gram language models. Results using the 1996 and 1997 DARPA Hub4 evaluation data sets are presented.