ISCA Archive Eurospeech 2001
ISCA Archive Eurospeech 2001

Speech recognition for huge vocabularies by using optimized sub-word units

Jan Kneissler, Dietrich Klakow

This paper describes approaches for decomposing words of huge vocabularies (up to 2 million) into smaller particles that are suitable for a recognition lexicon. Results on a Finnish dictation task and a flat list of German street names are given.