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

Tctkashi Otsuki; Akinori Ito; Shozo Makino; Teruhiko Otomo

doi:10.1109/ICASSP.1994.389272

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

Tctkashi Otsuki, Akinori Ito, Shozo Makino, Teruhiko Otomo

ENG - Communications Engineering

Research output: Contribution to journal › Conference article › peer-review

1 Citation (Scopus)

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.

Original language	English
Article number	389272
Pages (from-to)	I397-I400
Journal	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	1
DOIs	https://doi.org/10.1109/ICASSP.1994.389272
Publication status	Published - 1994
Event	Proceedings of the 1994 IEEE International Conference on Acoustics, Speech and Signal Processing. Part 2 (of 6) - Adelaide, Aust Duration: 1994 Apr 19 → 1994 Apr 22

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.1994.389272

Cite this

@article{2b052c53ed9042eb928f9f447cdc8eda,

title = "The performance prediction method on sentence recognition system using a finite state automaton",

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.",

author = "Tctkashi Otsuki and Akinori Ito and Shozo Makino and Teruhiko Otomo",

note = "Publisher Copyright: {\textcopyright} 1994 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.; Proceedings of the 1994 IEEE International Conference on Acoustics, Speech and Signal Processing. Part 2 (of 6) ; Conference date: 19-04-1994 Through 22-04-1994",

year = "1994",

doi = "10.1109/ICASSP.1994.389272",

language = "English",

volume = "1",

pages = "I397--I400",

journal = "Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing",

issn = "0736-7791",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - The performance prediction method on sentence recognition system using a finite state automaton

AU - Otsuki, Tctkashi

AU - Ito, Akinori

AU - Makino, Shozo

AU - Otomo, Teruhiko

PY - 1994

Y1 - 1994

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85079104154&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85079104154&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.1994.389272

DO - 10.1109/ICASSP.1994.389272

M3 - Conference article

AN - SCOPUS:85079104154

SN - 0736-7791

VL - 1

SP - I397-I400

JO - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

JF - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

M1 - 389272

T2 - Proceedings of the 1994 IEEE International Conference on Acoustics, Speech and Signal Processing. Part 2 (of 6)

Y2 - 19 April 1994 through 22 April 1994

ER -

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

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this