Label	96mue2
Title	Predicting the Out-of-Vocabulary Rate and the Required Vocabulary Size for Speech Processing Applications
Authors	Johannes Müller, Holger Stahl, Manfred Lang
Type	Scientific Conference Paper
Abstract	This paper describes an approach for predicting both the vocabulary size and the resulting out-of-vocabulary rate (OOV-rate) for a hypothetical extension of an existing text corpus. By splitting the original corpus into two different sub-corpora, vocabulary and OOV-rate can be determined for that special constellation. Average values are calculated for all combinations of sub-corpora and can be approximated by analytic function terms. These functions enable the easy prediction of the vocabulary size and the OOV-rate. The prediction accuracy results in a relative error below 4.6%. Keywords: out-of-vocabulary rate, OOV-rate, vocabulary size, text corpus, test corpus, training corpus
Reference	Proceedings ICSLP 96 (Philadelphia, USA, 1996), pp. 658-661  doi.org/10.1109/ICSLP.1996.608010
Published	October 1996
Language	English
Download	Scientific Conference Paper as pdf file  (48 kByte)