SPEAKER-INDEPENDENT CONNECTED WORDS RECOGNITION USING VECTOR QUANTIZATION OF THE TIME-SPACE PATTERN.

Satoru Hayamizu; Ryu ichi Oka

SPEAKER-INDEPENDENT CONNECTED WORDS RECOGNITION USING VECTOR QUANTIZATION OF THE TIME-SPACE PATTERN.

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

This paper describes an attempt on the word recognition using a matrix of feature vectors as a description unit for a time pattern. Pseudo-phoneme patterns represented by the matrices are extracted in advance by a vector quantization. The connected words recognition is conducted using these pseudo-phoneme patterns and Continuous Dynamic Programming. Distance measures among matrices and an algorithm of the vector quantization are described. Results of preparatory experiment are shown for 54 city names.

Original language	English
Pages (from-to)	160-163
Number of pages	4
Journal	Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory
Volume	50
Issue number	2-3
Publication status	Published - 1986
Externally published	Yes

ASJC Scopus subject areas

Condensed Matter Physics
Electrical and Electronic Engineering

Cite this

@article{ff0a7606f69744cdb1c52bae1aa494a2,

title = "SPEAKER-INDEPENDENT CONNECTED WORDS RECOGNITION USING VECTOR QUANTIZATION OF THE TIME-SPACE PATTERN.",

abstract = "This paper describes an attempt on the word recognition using a matrix of feature vectors as a description unit for a time pattern. Pseudo-phoneme patterns represented by the matrices are extracted in advance by a vector quantization. The connected words recognition is conducted using these pseudo-phoneme patterns and Continuous Dynamic Programming. Distance measures among matrices and an algorithm of the vector quantization are described. Results of preparatory experiment are shown for 54 city names.",

author = "Satoru Hayamizu and Oka, {Ryu ichi}",

year = "1986",

language = "English",

volume = "50",

pages = "160--163",

journal = "Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory",

issn = "0366-9092",

publisher = "Denshi Gijutsu Sogo Kenkyujo",

number = "2-3",

}

TY - JOUR

T1 - SPEAKER-INDEPENDENT CONNECTED WORDS RECOGNITION USING VECTOR QUANTIZATION OF THE TIME-SPACE PATTERN.

AU - Hayamizu, Satoru

AU - Oka, Ryu ichi

PY - 1986

Y1 - 1986

N2 - This paper describes an attempt on the word recognition using a matrix of feature vectors as a description unit for a time pattern. Pseudo-phoneme patterns represented by the matrices are extracted in advance by a vector quantization. The connected words recognition is conducted using these pseudo-phoneme patterns and Continuous Dynamic Programming. Distance measures among matrices and an algorithm of the vector quantization are described. Results of preparatory experiment are shown for 54 city names.

AB - This paper describes an attempt on the word recognition using a matrix of feature vectors as a description unit for a time pattern. Pseudo-phoneme patterns represented by the matrices are extracted in advance by a vector quantization. The connected words recognition is conducted using these pseudo-phoneme patterns and Continuous Dynamic Programming. Distance measures among matrices and an algorithm of the vector quantization are described. Results of preparatory experiment are shown for 54 city names.

UR - http://www.scopus.com/inward/record.url?scp=0022524081&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0022524081&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0022524081

SN - 0366-9092

VL - 50

SP - 160

EP - 163

JO - Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory

JF - Denshi Gijutsu Sogo Kenkyusho Iho/Bulletin of the Electrotechnical Laboratory

IS - 2-3

ER -

SPEAKER-INDEPENDENT CONNECTED WORDS RECOGNITION USING VECTOR QUANTIZATION OF THE TIME-SPACE PATTERN.

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this