Bitte benutzen Sie diese Referenz, um auf diese Ressource zu verweisen: doi:10.22028/D291-25260
Titel: What's in a word graph evaluation and enhancement of word lattices
Verfasser: Amtrup, Jan W.
Heine, Henrik
Jost, Uwe
Sprache: Englisch
Erscheinungsjahr: 1996
SWD-Schlagwörter: Künstliche Intelligenz
Freie Schlagwörter: artificial intelligence
DDC-Sachgruppe: 004 Informatik
Dokumentart : Report (Bericht)
Kurzfassung: During the last few years, word graphs have been gaining increasing interest within the speech community as the primary interface between speech recognizers and language processing modules. Both development and evaluation of graph-producing speech decoders require generally accepted measures of word graph quality. While the notion of recognition accuracy can easily be extended to word graphs, a meaningful measure of word graph size has not yet surfaced. We argue, that the number of derivation steps a theoretical parser would need to process all unique sub-paths in a graph could provide a measure that is both application oriented enough to be meaningful and general enough to allow a useful comparison of word recognizers across different applications. This paper discusses various measures that are used, or could be used, to measure word graph quality. Using real-life data (word graphs evaluated in the 1996 Verbmobil acoustic evaluation), it is demonstrated how different measures can affect evaluation results. Finally, some algorithms are presented that can significantly improve word graph quality with respect to specific quality measures.
Link zu diesem Datensatz: urn:nbn:de:bsz:291-scidok-53757
hdl:20.500.11880/25316
http://dx.doi.org/10.22028/D291-25260
Schriftenreihe: Vm-Report / Verbmobil, Verbundvorhaben, [Deutsches Forschungszentrum für Künstliche Intelligenz]
Band: 186
SciDok-Publikation: 7-Jun-2013
Fakultät: Sonstige Einrichtungen
Fachrichtung: SE - DFKI Deutsches Forschungszentrum für Künstliche Intelligenz
Fakultät / Institution:SE - Sonstige Einrichtungen

Dateien zu dieser Ressource:
Datei Beschreibung GrößeFormat 
Vm_186.pdf16,87 MBAdobe PDFÖffnen/Anzeigen


Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt.