4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

A Comparison of Time Conditioned and Word Conditioned Search Techniques for Large Vocabulary Speech Recognition

S. Ortmanns (1), Hermann Ney (1), Frank Seide (1,2), I. Lindam (1)

(1) Lehrstuhl für Informatik VI, RWTH Aachen, University of Technology, Aachen, Germany
(2) Philips GmbH Forschungslaboratorien, Aachen, Germany

In this paper, we compare the search effort of the word conditioned and the time conditioned tree search methods. Both methods are based on a time-synchronous, left-to-right beam search using a tree-organized lexicon. Whereas the word conditioned method is well known and widely used, the time conditioned method is novel in the context of 20.000 word vocabulary recognition. We extend both methods to handle trigram language models in a one-pass strategy. Both methods were tested on a train schedule inquiry task (1.850 words, telephone speech) and on the North American Business (Nov.’94) development corpus (20.000 words).

Full Paper

Bibliographic reference.  Ortmanns, S. / Ney, Hermann / Seide, Frank / Lindam, I. (1996): "A comparison of time conditioned and word conditioned search techniques for large vocabulary speech recognition", In ICSLP-1996, 2091-2094.