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.
s/h4> 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.
Cite as: Novák, M. (2009) Incremental composition of static decoding graphs. Proc. Interspeech 2009, 1175-1178, doi: 10.21437/Interspeech.2009-341
@inproceedings{novak09_interspeech,
author={Miroslav Novák},
title={{Incremental composition of static decoding graphs}},
year=2009,
booktitle={Proc. Interspeech 2009},
pages={1175--1178},
doi={10.21437/Interspeech.2009-341}
}