Efficient Language Model Lookahead through Polymorphic Linguistic Context Assignment

May 2002

Efficient Language Model Lookahead through Polymorphic Linguistic Context Assignment

Authors:

Hagen Soltau, Florian Metze, Christian F?en, and Alex Waibel

Abstract:

In this study, we examine how fast decoding of conversational speech with large vocabularies profits from efficient use of linguistic information, i.e. language models and grammars. Based on a re-entrant single pronunciation prefix tree, we use the concept of linguistic context polymorphism to achieve an early incorporation of language model information. This approach allows us to use all available language model information in a one-pass decoder, using the same engine to decode with statistical n-gram language models as well as context free grammars or re-scoring of lattices in an efficient way. We compare this approach to our previous decoder, which needed three passes to incorporate all available information. The results on a very large vocabulary task show that the search can be speeded up by almost a factor of three, without introducing additional search errors. On all examined tasks, we observed significant improvements by using an exact language model lookahead over usual bigram lookahead strategies, even for very hard tasks with unmatched conditions, without introducing extra memory overhead.
@conference{Soltau-2002-8455,
author = {Hagen Soltau And Florian Metze And Christian F?en And Alex Waibel},
title = {Efficient Language Model Lookahead through Polymorphic Linguistic Context Assignment},
booktitle = {Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '02)},
year = {2002},
month = {May},
pages = {709 - 712},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.