Lattice-based search strategies for large vocabulary speech recognition
Frederico Leite Richardson, Mari Ostendorf, Jan Robin Rohlicek · 2002
The design of search algorithms is an important issue in large vocabulary speech recognition, especially as more complex models are developed for improving recognition accuracy. Multi-pass search strategies have been used as a means of applying simple models early on to prune the search space for subsequent passes using more expensive knowledge sources. The pruned search space is typically represented by an N-best sentence list or a word lattice. Here, we investigate three alternatives for lattice search: N-best rescoring, a lattice dynamic programming search algorithm and a lattice local search algorithm. Both the lattice dynamic programming and lattice local search algorithms are shown to achieve comparable performance to the N-best search algorithm while running as much as 10 times faster on a 20 k word lexicon; the local search algorithm has the additional advantage of accommodating sentence-level knowledge sources.