DocumentCode
2279913
Title
Very large vocabulary proper name recognition for directory assistance
Author
Béchet, Frédéric ; de Mori, Renato ; Subsol, Gérard
Author_Institution
Univ. of Avignon, France
fYear
2001
fDate
2001
Firstpage
222
Lastpage
225
Abstract
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.
Keywords
computer telephony integration; speech recognition; vocabulary; directory assistance; hypothesis generation; proper name recognition; speech recognition; very large vocabulary; Acoustic distortion; Automatic speech recognition; Error analysis; Hidden Markov models; Lattices; Research and development; Robustness; Speech recognition; Vocabulary;
fLanguage
English
Publisher
ieee
Conference_Titel
Automatic Speech Recognition and Understanding, 2001. ASRU '01. IEEE Workshop on
Print_ISBN
0-7803-7343-X
Type
conf
DOI
10.1109/ASRU.2001.1034627
Filename
1034627
Link To Document