METHOD OF USING LINGUISTIC INFORMATION FOR AUTOMATIC SPOKEN WORD RECOGNITION.

Yoshihiro Niitsu, Jouji Miwa, Shozo Makino, Ken'iti Kido

Research output: Contribution to journalArticle

Abstract

The likelihood between phonemes is given by a confusion matrix based on the result of phoneme recognition and a method of matching with a word dictionary is proposed using dynamic programming with consideration of the probabilities of phoneme addition and omission. Using the proposed method, experiments in spoken word recognition are performed for a number of speakers and the effectiveness of the method is examined. The reliability of the confusion matrix is examined and it is shown that the proposed method is also effective for unspecified speakers. The results of recognition experiments for 25 male adults (including 10 unspecified speakers) were 84. 0, 95. 0 and 97. 2%, respectively, for 166, 51 and 20 city names.

Original languageEnglish
Pages (from-to)17-26
Number of pages10
JournalSystems, computers, controls
Volume10
Issue number1
Publication statusPublished - 1979 Jan 1
Externally publishedYes

Fingerprint

Linguistics
Glossaries
Dynamic programming
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

METHOD OF USING LINGUISTIC INFORMATION FOR AUTOMATIC SPOKEN WORD RECOGNITION. / Niitsu, Yoshihiro; Miwa, Jouji; Makino, Shozo; Kido, Ken'iti.

In: Systems, computers, controls, Vol. 10, No. 1, 01.01.1979, p. 17-26.

Research output: Contribution to journalArticle

Niitsu, Yoshihiro ; Miwa, Jouji ; Makino, Shozo ; Kido, Ken'iti. / METHOD OF USING LINGUISTIC INFORMATION FOR AUTOMATIC SPOKEN WORD RECOGNITION. In: Systems, computers, controls. 1979 ; Vol. 10, No. 1. pp. 17-26.
@article{881b4fcee3324239b11351c47d7d1029,
title = "METHOD OF USING LINGUISTIC INFORMATION FOR AUTOMATIC SPOKEN WORD RECOGNITION.",
abstract = "The likelihood between phonemes is given by a confusion matrix based on the result of phoneme recognition and a method of matching with a word dictionary is proposed using dynamic programming with consideration of the probabilities of phoneme addition and omission. Using the proposed method, experiments in spoken word recognition are performed for a number of speakers and the effectiveness of the method is examined. The reliability of the confusion matrix is examined and it is shown that the proposed method is also effective for unspecified speakers. The results of recognition experiments for 25 male adults (including 10 unspecified speakers) were 84. 0, 95. 0 and 97. 2{\%}, respectively, for 166, 51 and 20 city names.",
author = "Yoshihiro Niitsu and Jouji Miwa and Shozo Makino and Ken'iti Kido",
year = "1979",
month = "1",
day = "1",
language = "English",
volume = "10",
pages = "17--26",
journal = "Systems, computers, controls",
issn = "0096-8765",
publisher = "Scripta Pub Co.",
number = "1",

}

TY - JOUR

T1 - METHOD OF USING LINGUISTIC INFORMATION FOR AUTOMATIC SPOKEN WORD RECOGNITION.

AU - Niitsu, Yoshihiro

AU - Miwa, Jouji

AU - Makino, Shozo

AU - Kido, Ken'iti

PY - 1979/1/1

Y1 - 1979/1/1

N2 - The likelihood between phonemes is given by a confusion matrix based on the result of phoneme recognition and a method of matching with a word dictionary is proposed using dynamic programming with consideration of the probabilities of phoneme addition and omission. Using the proposed method, experiments in spoken word recognition are performed for a number of speakers and the effectiveness of the method is examined. The reliability of the confusion matrix is examined and it is shown that the proposed method is also effective for unspecified speakers. The results of recognition experiments for 25 male adults (including 10 unspecified speakers) were 84. 0, 95. 0 and 97. 2%, respectively, for 166, 51 and 20 city names.

AB - The likelihood between phonemes is given by a confusion matrix based on the result of phoneme recognition and a method of matching with a word dictionary is proposed using dynamic programming with consideration of the probabilities of phoneme addition and omission. Using the proposed method, experiments in spoken word recognition are performed for a number of speakers and the effectiveness of the method is examined. The reliability of the confusion matrix is examined and it is shown that the proposed method is also effective for unspecified speakers. The results of recognition experiments for 25 male adults (including 10 unspecified speakers) were 84. 0, 95. 0 and 97. 2%, respectively, for 166, 51 and 20 city names.

UR - http://www.scopus.com/inward/record.url?scp=0018334751&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0018334751&partnerID=8YFLogxK

M3 - Article

VL - 10

SP - 17

EP - 26

JO - Systems, computers, controls

JF - Systems, computers, controls

SN - 0096-8765

IS - 1

ER -