SPOKEN WORD RECOGNITION SYSTEM FOR UNLIMITED SPEAKERS.

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

Research output: Contribution to conferencePaper

Abstract

The newly improved spoken word recognition system is described. The accuracy of the word recognition is improved by implementing new features extraction method and new phoneme connecting rules in addition to the previously reported system. The new features for the phoneme recognition are the spectral local peaks and four parameters by using the least squares fit line of speech spectrum. By increasing the features for the phoneme recognition, and by using new phoneme connecting rules, the accuracies of phoneme recognition and segmentation are improved. In the last step of the system, the item of the dictionary having maximum similarity to the recognized phonemic sequence is chosen. Every item of the dictionary is written in phonemic symbols, and it easy to change the objective words. The score of the word recognition was found to be 85. 7% for 166 city names uttered by 15 male speakers.

Original languageEnglish
Pages735-738
Number of pages4
Publication statusPublished - 2017 Jan 1
EventRec IEEE Int Conf Acoust Speech Signal Process 3rd - Tulsa, OK, USA
Duration: 1978 Apr 101978 Apr 12

Conference

ConferenceRec IEEE Int Conf Acoust Speech Signal Process 3rd
CityTulsa, OK, USA
Period78/4/1078/4/12

Fingerprint

Glossaries
Feature extraction

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Kido, K., Miwa, J., Makino, S., & Niitsu, Y. (2017). SPOKEN WORD RECOGNITION SYSTEM FOR UNLIMITED SPEAKERS.. 735-738. Paper presented at Rec IEEE Int Conf Acoust Speech Signal Process 3rd, Tulsa, OK, USA, .

SPOKEN WORD RECOGNITION SYSTEM FOR UNLIMITED SPEAKERS. / Kido, Ken'iti; Miwa, Jouji; Makino, Shozo; Niitsu, Yoshihiro.

2017. 735-738 Paper presented at Rec IEEE Int Conf Acoust Speech Signal Process 3rd, Tulsa, OK, USA, .

Research output: Contribution to conferencePaper

Kido, K, Miwa, J, Makino, S & Niitsu, Y 2017, 'SPOKEN WORD RECOGNITION SYSTEM FOR UNLIMITED SPEAKERS.' Paper presented at Rec IEEE Int Conf Acoust Speech Signal Process 3rd, Tulsa, OK, USA, 78/4/10 - 78/4/12, pp. 735-738.
Kido K, Miwa J, Makino S, Niitsu Y. SPOKEN WORD RECOGNITION SYSTEM FOR UNLIMITED SPEAKERS.. 2017. Paper presented at Rec IEEE Int Conf Acoust Speech Signal Process 3rd, Tulsa, OK, USA, .
Kido, Ken'iti ; Miwa, Jouji ; Makino, Shozo ; Niitsu, Yoshihiro. / SPOKEN WORD RECOGNITION SYSTEM FOR UNLIMITED SPEAKERS. Paper presented at Rec IEEE Int Conf Acoust Speech Signal Process 3rd, Tulsa, OK, USA, .4 p.
@conference{6fd3604208614c2b94642940b4918d9e,
title = "SPOKEN WORD RECOGNITION SYSTEM FOR UNLIMITED SPEAKERS.",
abstract = "The newly improved spoken word recognition system is described. The accuracy of the word recognition is improved by implementing new features extraction method and new phoneme connecting rules in addition to the previously reported system. The new features for the phoneme recognition are the spectral local peaks and four parameters by using the least squares fit line of speech spectrum. By increasing the features for the phoneme recognition, and by using new phoneme connecting rules, the accuracies of phoneme recognition and segmentation are improved. In the last step of the system, the item of the dictionary having maximum similarity to the recognized phonemic sequence is chosen. Every item of the dictionary is written in phonemic symbols, and it easy to change the objective words. The score of the word recognition was found to be 85. 7{\%} for 166 city names uttered by 15 male speakers.",
author = "Ken'iti Kido and Jouji Miwa and Shozo Makino and Yoshihiro Niitsu",
year = "2017",
month = "1",
day = "1",
language = "English",
pages = "735--738",
note = "Rec IEEE Int Conf Acoust Speech Signal Process 3rd ; Conference date: 10-04-1978 Through 12-04-1978",

}

TY - CONF

T1 - SPOKEN WORD RECOGNITION SYSTEM FOR UNLIMITED SPEAKERS.

AU - Kido, Ken'iti

AU - Miwa, Jouji

AU - Makino, Shozo

AU - Niitsu, Yoshihiro

PY - 2017/1/1

Y1 - 2017/1/1

N2 - The newly improved spoken word recognition system is described. The accuracy of the word recognition is improved by implementing new features extraction method and new phoneme connecting rules in addition to the previously reported system. The new features for the phoneme recognition are the spectral local peaks and four parameters by using the least squares fit line of speech spectrum. By increasing the features for the phoneme recognition, and by using new phoneme connecting rules, the accuracies of phoneme recognition and segmentation are improved. In the last step of the system, the item of the dictionary having maximum similarity to the recognized phonemic sequence is chosen. Every item of the dictionary is written in phonemic symbols, and it easy to change the objective words. The score of the word recognition was found to be 85. 7% for 166 city names uttered by 15 male speakers.

AB - The newly improved spoken word recognition system is described. The accuracy of the word recognition is improved by implementing new features extraction method and new phoneme connecting rules in addition to the previously reported system. The new features for the phoneme recognition are the spectral local peaks and four parameters by using the least squares fit line of speech spectrum. By increasing the features for the phoneme recognition, and by using new phoneme connecting rules, the accuracies of phoneme recognition and segmentation are improved. In the last step of the system, the item of the dictionary having maximum similarity to the recognized phonemic sequence is chosen. Every item of the dictionary is written in phonemic symbols, and it easy to change the objective words. The score of the word recognition was found to be 85. 7% for 166 city names uttered by 15 male speakers.

UR - http://www.scopus.com/inward/record.url?scp=0017791711&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0017791711&partnerID=8YFLogxK

M3 - Paper

SP - 735

EP - 738

ER -