Improved multisection vector quantization model with application to Chinese digits recognition

Rong Zhang; Zhaoxiong Chen; Heyan Huang

Improved multisection vector quantization model with application to Chinese digits recognition

Rong Zhang^*, Zhaoxiong Chen, Heyan Huang

^*Corresponding author for this work

Chinese Academy of Sciences

Research output: Contribution to conference › Paper › peer-review

Abstract

In this paper, an improved model using Multisection Vector Quantization (MVQ) is proposed and detailed experimental results are discussed. The major weakness of conventional MVQ is that it can not make segment accurately. So a dynamic segmenting algorithm based on Viterbi algorithm is presented. Moreover explicit state duration density and dynamic features are integrated into model. Thus more acoustic information is depicted and a better performance is acquired.

Original language	English
Pages	749-752
Number of pages	4
Publication status	Published - 1996
Externally published	Yes
Event	Proceedings of the 1996 3rd International Conference on Signal Processing, ICSP'96. Part 1 (of 2) - Beijing, China Duration: 14 Oct 1996 → 18 Oct 1996

Conference

Conference	Proceedings of the 1996 3rd International Conference on Signal Processing, ICSP'96. Part 1 (of 2)
City	Beijing, China
Period	14/10/96 → 18/10/96

Cite this

@conference{55af3a1b544e4b66b4f4820147213f9f,

title = "Improved multisection vector quantization model with application to Chinese digits recognition",

abstract = "In this paper, an improved model using Multisection Vector Quantization (MVQ) is proposed and detailed experimental results are discussed. The major weakness of conventional MVQ is that it can not make segment accurately. So a dynamic segmenting algorithm based on Viterbi algorithm is presented. Moreover explicit state duration density and dynamic features are integrated into model. Thus more acoustic information is depicted and a better performance is acquired.",

author = "Rong Zhang and Zhaoxiong Chen and Heyan Huang",

year = "1996",

language = "English",

pages = "749--752",

note = "Proceedings of the 1996 3rd International Conference on Signal Processing, ICSP'96. Part 1 (of 2) ; Conference date: 14-10-1996 Through 18-10-1996",

}

TY - CONF

T1 - Improved multisection vector quantization model with application to Chinese digits recognition

AU - Zhang, Rong

AU - Chen, Zhaoxiong

AU - Huang, Heyan

PY - 1996

Y1 - 1996

N2 - In this paper, an improved model using Multisection Vector Quantization (MVQ) is proposed and detailed experimental results are discussed. The major weakness of conventional MVQ is that it can not make segment accurately. So a dynamic segmenting algorithm based on Viterbi algorithm is presented. Moreover explicit state duration density and dynamic features are integrated into model. Thus more acoustic information is depicted and a better performance is acquired.

AB - In this paper, an improved model using Multisection Vector Quantization (MVQ) is proposed and detailed experimental results are discussed. The major weakness of conventional MVQ is that it can not make segment accurately. So a dynamic segmenting algorithm based on Viterbi algorithm is presented. Moreover explicit state duration density and dynamic features are integrated into model. Thus more acoustic information is depicted and a better performance is acquired.

UR - http://www.scopus.com/inward/record.url?scp=0030383347&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0030383347

SP - 749

EP - 752

T2 - Proceedings of the 1996 3rd International Conference on Signal Processing, ICSP'96. Part 1 (of 2)

Y2 - 14 October 1996 through 18 October 1996

ER -

Improved multisection vector quantization model with application to Chinese digits recognition

Abstract

Conference

Other files and links

Fingerprint

Cite this