@inproceedings{4eedbfe2492e470daa926bec23d5c738,
title = "Compound Decomposition in Dutch Large Vocabulary Speech Recognition",
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.",
keywords = "Spoken Document Retrieval, Audio search, HMI-MR: MULTIMEDIA RETRIEVAL, HMI-SLT: Speech and Language Technology, METIS-217551, IR-63377, EWI-6705",
author = "Ordelman, {Roeland J.F.} and {van Hessen}, {Adrianus J.} and {de Jong}, {Franciska M.G.}",
note = "Imported from HMI; Eurospeech 2003 ; Conference date: 01-09-2003 Through 04-09-2003",
year = "2003",
language = "Undefined",
publisher = "ISCA",
pages = "--",
booktitle = "Eurospeech 2003",
}