A speech understanding system based on statistical representation of semantics

Author

Pieraccini, Roberto ; Tzoukermann, Evelyne ; Gorelov, Zakhar ; Gauvain, Jean-Luc ; Levin, Esther ; Lee, Chin-Hui ; Wilpon, Jay G.

Author_Institution

AT&T Bell Labs., Murray Hill, NJ, USA

Volume

1

fYear

1992

fDate

23-26 Mar 1992

Firstpage

193

Abstract

An understanding system, designed for both speech and text input, has been implemented based on statistical representation of task specific semantic knowledge. The core of the system is the conceptual decoder, which extracts the words and their association to the conceptual structure of the task directly from the acoustic signal. The conceptual information, which is also used to clarify the English sentences, is encoded following a statistical paradigm. A template generator and an SQL (structured query language) translator process the sentence and produce SQL code for querying a relational database. Results of the system on the official DARPA test are given

Keywords

SQL; natural languages; relational databases; speech recognition; statistical analysis; DARPA test; English sentences; SQL code; SQL translator; acoustic signal; conceptual decoder; conceptual information; conceptual structure; relational database; semantics; speech understanding system; statistical paradigm; statistical representation; structured query language; template generator; text input; Acoustic measurements; Acoustic signal detection; Acoustic testing; Data mining; Databases; Decoding; Information retrieval; Knowledge representation; Speech recognition; System testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on

Conference_Location

San Francisco, CA

ISSN

1520-6149

Print_ISBN

0-7803-0532-9

Type

conf

DOI

10.1109/ICASSP.1992.225939

Filename

225939