The 2001 BYBLOS English large vocabulary conversational speech recognition system

摘要

This paper describes the BYBLOS system that BBN used to participate in the 2001 NIST Hub-5 evaluation benchmark. We outline the procedure used for training and decoding, and present the algorithmic improvements made to the system, along with experimental results. These improvements include a Gaussian splitting initialization procedure, the use of linear discriminant analysis, and processing of additional acoustic training data. We also discuss our system combination and confidence-based thresholding methods. Experiments on an internal validation test set show that all these system improvements provide a 8.1% relative reduction in word error rate compared to our 2000 LVCSR system.