Very large vocabulary proper name recognition for directory assistance

Very large vocabulary proper name recognition for directory assistance

This paper deals with the difficult task of recognition of a large vocabulary of proper names in a directory assistance application. After a presentation of the related work, it introduces a methodology for rescoring the N-best hypotheses generated by a first step recognition. First experiments give...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bechet, F., de Mori, R., Subsol, G.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Acoustic distortion
Automatic speech recognition
Error analysis
Hidden Markov models
Lattices
Research and development
Robustness
Speech recognition
Vocabulary
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper deals with the difficult task of recognition of a large vocabulary of proper names in a directory assistance application. After a presentation of the related work, it introduces a methodology for rescoring the N-best hypotheses generated by a first step recognition. First experiments give encouraging results and several topics for future research are presented.
DOI:10.1109/ASRU.2001.1034627