10th Annual Conference of the International Speech Communication Association

Brighton, United Kingdom
September 6-10, 2009

Incremental Composition of Static Decoding Graphs

Miroslav Novák

IBM T.J. Watson Research Center, USA

A fast, scalable and memory-efficient method for static decoding graph construction is presented. As an alternative to the traditional transducer-based approach, it is based on incremental composition. Memory efficiency is achieved by combining composition, determinization and minimization into a single step, thus eliminating large intermediate graphs. We have previously reported the use of incremental composition limited to grammars and left cross-word context [1]. Here, this approach is extended to n-gram models with explicit å arcs and right cross-word context.

  1. M. Novak and V. Bergl, “Memory efficient decoding graph compilation with wide cross-word acoustic context”, In Proceedings of Interspeech 2004, 281-284, Seul, South Korea, 2004.

Full Paper

Bibliographic reference.  Novák, Miroslav (2009): "Incremental composition of static decoding graphs", In INTERSPEECH-2009, 1175-1178.