Forschungs- & Entwicklungsinformationsdienst der Gemeinschaft - CORDIS

ONOMASTICA: multi-language pronunciation dictionary of proper names

The work of the ONOMASTICA project has addressed aspects of names pronunciation to prepare recommendations for lexical definitions in creating an approach that would best guarantee the correct automatic pronunciation of the vast majority of names in a national telephone directory by creating a database of every person's name and its phonetic spelling. The project has produced a realization of a names pronunciation lexicon in compact disc read only memory (CDROM) form. The CDROM contains 4.5 million entries for high quality data in Quality Band I and Quality Band II which has been checked by human experts working on the project. The full ONOMASTICA lexicon of 8.5 million names is available on EXABYTE tape format since the capacity of the CDROM used is inadequate for all of the lexical data. The CDROM and EXABYTE tape have been distributed to 22 organizations throughout Europe.

Reported by

The University of Edinburgh
80 South Bridge
EH1 1HN Edinburgh
United Kingdom
See on map
Folgen Sie uns auf: RSS Facebook Twitter YouTube Verwaltet vom Amt für Veröffentlichungen der EU Nach oben