Matches in UGent Biblio for { <https://biblio.ugent.be/publication/1057867#aggregation> ?p ?o. }
Showing items 1 to 34 of
34
with 100 items per page.
- aggregation classification "C1".
- aggregation creator B84526.
- aggregation creator B84527.
- aggregation creator person.
- aggregation creator person.
- aggregation date "2010".
- aggregation format "application/pdf".
- aggregation hasFormat 1057867.bibtex.
- aggregation hasFormat 1057867.csv.
- aggregation hasFormat 1057867.dc.
- aggregation hasFormat 1057867.didl.
- aggregation hasFormat 1057867.doc.
- aggregation hasFormat 1057867.json.
- aggregation hasFormat 1057867.mets.
- aggregation hasFormat 1057867.mods.
- aggregation hasFormat 1057867.rdf.
- aggregation hasFormat 1057867.ris.
- aggregation hasFormat 1057867.txt.
- aggregation hasFormat 1057867.xls.
- aggregation hasFormat 1057867.yaml.
- aggregation isPartOf urn:issn:1990-9772.
- aggregation language "eng".
- aggregation publisher "International Speech Communication Association (ISCA)".
- aggregation rights "I have transferred the copyright for this publication to the publisher".
- aggregation subject "Science General".
- aggregation title "A minimum classification error approach to pronunciation variation modeling of non-native proper names".
- aggregation abstract "In automatic recognition of non-native proper names, it is critical to be able to handle a variety of different pronunciations. Traditionally, this has been solved by including alternative pronunciation variants in the recognition lexicon at the risk of introducing unwanted confusion between different name entries. In this paper we propose a pronunciation variant selection criterion that aims to avoid this risk by basing its decisions on scores which are calculated according to the minimum classification error (MCE) framework. By comparing the error rate before and after a lexicon change, the selection criterion chooses only the candidates that actually decrease the error rate. Selecting pronunciation candidates in this manner substantially reduces both the error rate and the required number of variants per name compared to a probability-based baseline selection method.".
- aggregation authorList BK217615.
- aggregation endPage "2285".
- aggregation startPage "2282".
- aggregation volume "2010".
- aggregation aggregates 1057887.
- aggregation isDescribedBy 1057867.
- aggregation similarTo LU-1057867.