Relationship among Recognition Rate, Rejection Rate and False Alarm Rate in a Spoken Word Recognition System

Atsuhiko KAI; Seiichi NAKAGAWA

Relationship among Recognition Rate, Rejection Rate and False Alarm Rate in a Spoken Word Recognition System

Atsuhiko KAI, Seiichi NAKAGAWA

Full Text Views

0

Share
Cite this

Summary :

Detection of an unknown word or non-vocabulary word uttered by the user is necessary in realizing a practical spoken language user-interface. This paper describes the evaluation of an unknown word processing method for a subword unit based spoken word recognizer. We have assessed the relationship between the word recognition accuracy of a system and the detection rate of unknown words both by simulation and by experiment of the unknown word processing method. We found that the resultant detection accuracies using the unknown word processing are significantly influenced by the original word recognition accuracy while the degree of such effect depends on the vocabulary size.

Publication: IEICE TRANSACTIONS on Information Vol.E78-D No.6 pp.698-704

Publication Date: 1995/06/25

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Issue on Spoken Language Processing)

Category

Cite this

Copy

Atsuhiko KAI, Seiichi NAKAGAWA, "Relationship among Recognition Rate, Rejection Rate and False Alarm Rate in a Spoken Word Recognition System" in IEICE TRANSACTIONS on Information, vol. E78-D, no. 6, pp. 698-704, June 1995, doi: .
Abstract: Detection of an unknown word or non-vocabulary word uttered by the user is necessary in realizing a practical spoken language user-interface. This paper describes the evaluation of an unknown word processing method for a subword unit based spoken word recognizer. We have assessed the relationship between the word recognition accuracy of a system and the detection rate of unknown words both by simulation and by experiment of the unknown word processing method. We found that the resultant detection accuracies using the unknown word processing are significantly influenced by the original word recognition accuracy while the degree of such effect depends on the vocabulary size.
URL: https://globals.ieice.org/en_transactions/information/10.1587/e78-d_6_698/_p

Copy

@ARTICLE{e78-d_6_698,
author={Atsuhiko KAI, Seiichi NAKAGAWA, },
journal={IEICE TRANSACTIONS on Information},
title={Relationship among Recognition Rate, Rejection Rate and False Alarm Rate in a Spoken Word Recognition System},
year={1995},
volume={E78-D},
number={6},
pages={698-704},
abstract={Detection of an unknown word or non-vocabulary word uttered by the user is necessary in realizing a practical spoken language user-interface. This paper describes the evaluation of an unknown word processing method for a subword unit based spoken word recognizer. We have assessed the relationship between the word recognition accuracy of a system and the detection rate of unknown words both by simulation and by experiment of the unknown word processing method. We found that the resultant detection accuracies using the unknown word processing are significantly influenced by the original word recognition accuracy while the degree of such effect depends on the vocabulary size.},
keywords={},
doi={},
ISSN={},
month={June},}

Copy

TY - JOUR
TI - Relationship among Recognition Rate, Rejection Rate and False Alarm Rate in a Spoken Word Recognition System
T2 - IEICE TRANSACTIONS on Information
SP - 698
EP - 704
AU - Atsuhiko KAI
AU - Seiichi NAKAGAWA
PY - 1995
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E78-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 1995
AB - Detection of an unknown word or non-vocabulary word uttered by the user is necessary in realizing a practical spoken language user-interface. This paper describes the evaluation of an unknown word processing method for a subword unit based spoken word recognizer. We have assessed the relationship between the word recognition accuracy of a system and the detection rate of unknown words both by simulation and by experiment of the unknown word processing method. We found that the resultant detection accuracies using the unknown word processing are significantly influenced by the original word recognition accuracy while the degree of such effect depends on the vocabulary size.
ER -