Abstract | ||
---|---|---|
Many speech applications, most prominently telephonedirectory assistance, require the recognition ofproper names. However, the recognition of increasinglylarge sets of spoken names is difficult: Besides technicallimitations, very large recognition vocabularies containmany easily confused words or even homophones. Therefore,proper names are often spelled or both spoken andspelled.In this paper we compare the performance for propername recognition when a name is spoken only, spelled... |
Year | Venue | Keywords |
---|---|---|
1997 | EUROSPEECH | proper names |
Field | DocType | Citations |
Computer science,Speech recognition,Onomastics,Proper noun,Linguistics | Conference | 12 |
PageRank | References | Authors |
1.39 | 4 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael Meyer | 1 | 95 | 12.55 |
Hermann Hild | 2 | 233 | 126.06 |