Techniques for effective vocabulary selection

Simple item page
dc.creatorVenkataraman, Anand
dc.creatorWang, Wen
dc.date2003-06-04
dc.date.accessioned2026-07-07T03:19:46Z
dc.date.available2026-07-07T03:19:46Z
dc.descriptionThe vocabulary of a continuous speech recognition (CSR) system is a significant factor in determining its performance. In this paper, we present three principled approaches to select the target vocabulary for a particular domain by trading off between the target out-of-vocabulary (OOV) rate and vocabulary size. We evaluate these approaches against an ad-hoc baseline strategy. Results are presented in the form of OOV rate graphs plotted against increasing vocabulary size for each technique.
dc.description4 pages. To appear Proc. Eurospeech 2003, Geneva
dc.identifierhttps://arxiv.org/abs/cs/0306022
dc.identifierhttp://arxiv.org/abs/cs/0306022
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/31597
dc.subjectComputation and Language
dc.subjectArtificial Intelligence
dc.subjectI.2.6;I.2.7
dc.titleTechniques for effective vocabulary selection
dc.typetext

Files

Collections

arXiv