SELECTION OF WORD-CANDIDATES BASED ON VECTOR QUANTIZATION FOR SPEAKER INDEPENDENT WORD RECOGNITION.

Katsuhiko Shirai, Koji Sano, Kazunori Mano

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

A method to select word-candidates for speaker independent word recognition is described. LEP cepstral coefficients are used as feature vectors, and vector quantization method is used to quantize and compress the features in each analysis frame to obtain speaker independence. Experiments were carried out for 100 city names uttered by 10 speakers with good results.

Original languageEnglish
Title of host publicationBulletin of Centre for Informatics (Waseda University)
Pages68-75, 116
Volume3
Publication statusPublished - 1986 Mar
Externally publishedYes

Fingerprint

Vector quantization
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Shirai, K., Sano, K., & Mano, K. (1986). SELECTION OF WORD-CANDIDATES BASED ON VECTOR QUANTIZATION FOR SPEAKER INDEPENDENT WORD RECOGNITION. In Bulletin of Centre for Informatics (Waseda University) (Vol. 3, pp. 68-75, 116)

SELECTION OF WORD-CANDIDATES BASED ON VECTOR QUANTIZATION FOR SPEAKER INDEPENDENT WORD RECOGNITION. / Shirai, Katsuhiko; Sano, Koji; Mano, Kazunori.

Bulletin of Centre for Informatics (Waseda University). Vol. 3 1986. p. 68-75, 116.

Research output: Chapter in Book/Report/Conference proceedingChapter

Shirai, K, Sano, K & Mano, K 1986, SELECTION OF WORD-CANDIDATES BASED ON VECTOR QUANTIZATION FOR SPEAKER INDEPENDENT WORD RECOGNITION. in Bulletin of Centre for Informatics (Waseda University). vol. 3, pp. 68-75, 116.
Shirai K, Sano K, Mano K. SELECTION OF WORD-CANDIDATES BASED ON VECTOR QUANTIZATION FOR SPEAKER INDEPENDENT WORD RECOGNITION. In Bulletin of Centre for Informatics (Waseda University). Vol. 3. 1986. p. 68-75, 116
Shirai, Katsuhiko ; Sano, Koji ; Mano, Kazunori. / SELECTION OF WORD-CANDIDATES BASED ON VECTOR QUANTIZATION FOR SPEAKER INDEPENDENT WORD RECOGNITION. Bulletin of Centre for Informatics (Waseda University). Vol. 3 1986. pp. 68-75, 116
@inbook{1123a856ffc4411a89149a6c00fd9139,
title = "SELECTION OF WORD-CANDIDATES BASED ON VECTOR QUANTIZATION FOR SPEAKER INDEPENDENT WORD RECOGNITION.",
abstract = "A method to select word-candidates for speaker independent word recognition is described. LEP cepstral coefficients are used as feature vectors, and vector quantization method is used to quantize and compress the features in each analysis frame to obtain speaker independence. Experiments were carried out for 100 city names uttered by 10 speakers with good results.",
author = "Katsuhiko Shirai and Koji Sano and Kazunori Mano",
year = "1986",
month = "3",
language = "English",
volume = "3",
pages = "68--75, 116",
booktitle = "Bulletin of Centre for Informatics (Waseda University)",

}

TY - CHAP

T1 - SELECTION OF WORD-CANDIDATES BASED ON VECTOR QUANTIZATION FOR SPEAKER INDEPENDENT WORD RECOGNITION.

AU - Shirai, Katsuhiko

AU - Sano, Koji

AU - Mano, Kazunori

PY - 1986/3

Y1 - 1986/3

N2 - A method to select word-candidates for speaker independent word recognition is described. LEP cepstral coefficients are used as feature vectors, and vector quantization method is used to quantize and compress the features in each analysis frame to obtain speaker independence. Experiments were carried out for 100 city names uttered by 10 speakers with good results.

AB - A method to select word-candidates for speaker independent word recognition is described. LEP cepstral coefficients are used as feature vectors, and vector quantization method is used to quantize and compress the features in each analysis frame to obtain speaker independence. Experiments were carried out for 100 city names uttered by 10 speakers with good results.

UR - http://www.scopus.com/inward/record.url?scp=0022685305&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0022685305&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:0022685305

VL - 3

SP - 68-75, 116

BT - Bulletin of Centre for Informatics (Waseda University)

ER -