The performance prediction method on sentence recognition system using a finite state automaton

Author

Otsuki, Takashi ; Ito, Akinori ; Makino, Shozo ; Otomo, Teruhiko

Author_Institution

Fac. of Eng., Yamagata Univ., Yonezawa, Japan

Volume

i

fYear

1994

fDate

19-22 Apr 1994

Abstract

This paper presents the performance evaluation method on sentence recognition system which uses a finite state automaton. The relationship between word recognition score and sentence recognition score can be predicted using the number of word sequences at a short distance from the sentence. But it is not clear that how we get this number when the finite state automaton is used as linguistic information. Therefore, we propose the algorithm to calculate this number in polynomial time. Then we carry out the prediction using this method and the simulation to compare with the prediction, and it is shown that our method is usable when the quality of the word lattice is good

Keywords

finite automata; prediction theory; speech recognition; finite state automaton; linguistic information; performance evaluation method; performance prediction method; polynomial time; sentence recognition score; sentence recognition system; simulation; word lattice quality; word recognition score; word sequences; Automata; Automatic speech recognition; Dictionaries; Information processing; Lattices; Polynomials; Prediction methods; Predictive models; Speech recognition; Systems engineering education;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on

Conference_Location

Adelaide, SA

ISSN

1520-6149

Print_ISBN

0-7803-1775-0

Type

conf

DOI

10.1109/ICASSP.1994.389272

Filename

389272