A fast and memory-efficient N-gram language model lookup method for large vocabulary continuous speech recognition [An article from: Computer Speech & Language]

This digital document is a journal article from Computer Speech & Language, published by Elsevier in 2007. The article is delivered in HTML format and is available in your Amazon.com Media Library immediately after purchase. You can view it with any web browser.Description: Recently, minimum perfect hashing (MPH)-based language model (LM) lookup methods have been proposed for fast access of N-gram LM scores in lexical-tree based LVCSR (large vocabulary continuous speech recognition) decoding. Methods of node-based LM cache and LM context pre-computing (LMCP) have also been proposed to combine with MPH for further reduction of LM lookup time. Although these methods are effective, LM lookup still takes a large share of overall decoding time when trigram LM lookahead (LMLA) is used for lower word error rate than unigram or bigram LMLAs. Besides computation time, memory cost is also an important performance aspect of decoding systems. Most speedup methods for LM lookup obtain higher speed at the cost of increased memory demand, which makes system performance unpredictable when running on computers with smaller memory capacities. In this paper, an