Near Minimal Weighted Word Graphs for Post-processing Speech

Large vocabulary speech recognition applications can benefit from an efficient data structure for representing large numbers of acoustic hypotheses compactly. Word graphs or lattices generated by acoustic recognition engines are generally not compact and must be post-processed to keep lattice sizes small; however, algorithms designed for this task need to reduce the size of the lattice without either eliminating hypotheses or distorting their relative acoustic probabilities. In this paper, we will discuss the relevant criteria for measuring graph size, compare the advantages of two different structures for graphs, and introduce a new data structure and compression algorithm which give additional graph compression and maintain exact hypothesis path scores by storing probability information on both nodes and arcs within the graph.