Understanding spontaneous speech: the Phoenix system

Author

Ward, Wayne

Author_Institution

Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA

fYear

1991

fDate

14-17 Apr 1991

Firstpage

365

Abstract

The author describes the design of the Phoenix speech understanding system and reports on its current status. Phoenix is a system currently being developed at Carnegie Mellon University to understand spontaneous speech. The system has been implemented for an air travel information service (ATIS) task. In the ATIS task, novice users are asked to perform a task that requires getting information from the air travel database. Users compose the questions themselves, and are allowed to phrase the queries any way they choose. No explicit grammar or lexicon is given to the subject. This task presents several problems not found in real input. Not only is the speech not fluent, but the vocabulary and grammar are open. The results of the processing of both the speech and transcript data for subjects performing the task are reported

Keywords

information retrieval; speech recognition; user interfaces; Phoenix speech understanding system; air travel database; air travel information service; information retrieval; open grammar; open vocabulary; speech recognition; transcript data; Acoustic noise; Airports; Computer science; Context modeling; Databases; Error analysis; Speech analysis; Speech processing; Vocabulary; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference on

Conference_Location

Toronto, Ont.

ISSN

1520-6149

Print_ISBN

0-7803-0003-3

Type

conf

DOI

10.1109/ICASSP.1991.150352

Filename

150352