Compound Decomposition in Dutch Large Vocabulary Speech Recognition

Ordelman, Roeland and Hessen van, Arjan and Jong de, Franciska (2003) Compound Decomposition in Dutch Large Vocabulary Speech Recognition. In: Eurospeech 2003, September 1-4, 2003, Geneva, Switzerland.

PDF
Restricted to UT campus only: Request a copy
86Kb

Abstract:	This paper addresses compound splitting for Dutch in the context of broadcast news transcription. Language models were created using original text versions and text versions that were decomposed using a data-driven compound splitting algorithm. Language model performances were compared in terms of out-of- vocabulary rates and word error rates in a real-world broadcast news transcription task. It was concluded that compound splitting does improve ASR performance. Best results were obtained when frequent compounds were not decomposed.
Item Type:	Conference or Workshop Item
Faculty:	Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:	Human Media Interaction (HMI)
Link to this item:	http://purl.utwente.nl/publications/63377
Export this item as:	BibTeX EndNote HTML Citation Reference Manager

Repository Staff Only: item control page

Metis ID: 217551