Lexicon Optimization for Dutch Speech Recognition in Spoken Document Retrieval

Ordelman, Roeland and Hessen van, Arjan and Jong de, Franciska (2001) Lexicon Optimization for Dutch Speech Recognition in Spoken Document Retrieval. [Report]

PDF
Restricted to UT campus only
69Kb

Abstract:	In this paper, ongoing work concerning the language modelling and lexicon optimization of a Dutch speech recognition system for Spoken Document Retrieval is described: the collection and normalization of a training data set and the optimization of our recognition lexicon. Effects on lexical coverage of the amount of training data, of decompounding compound words and of different selection methods for proper names and acronyms are discussed.
Item Type:	Report
Faculty:	Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:	Human Media Interaction (HMI)
Link to this item:	http://purl.utwente.nl/publications/63098
Official URL:	http://www.ub.utwente.nl/webdocs/ctit/1/00000065.pdf
Export this item as:	BibTeX EndNote HTML Citation Reference Manager

Repository Staff Only: item control page