Isolated Mandarin base-syllable recognition based upon the segmentai probability model

Ren Yuan Lyu; I. Chung Hong; Jia Lin Shen; Ming Yu Lee; Lin Shan Lee

doi:10.1109/89.668823

Isolated Mandarin base-syllable recognition based upon the segmentai probability model

Ren Yuan Lyu^*
, I. Chung Hong
, Jia Lin Shen
, Ming Yu Lee
, Lin Shan Lee

^*Corresponding author for this work

Department of Computer Science and Information Engineering

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

9 Scopus citations

Abstract

In this correspondence, a segmental probability model (SPM) is proposed for fast and accurate recognition of the highly confusing isolated Mandarin base-syllables by deleting the state transition probabilities of continuous density hidden Markov models (CHMM), abandoning the dynamic programming process, letting the states equally segment the base-syllables deterministically, and using several special approaches to improve the accuracy and speed. This is achieved by considering the special characteristics of the target vocabulary.

Original language	English
Pages (from-to)	293-299
Number of pages	7
Journal	IEEE Transactions on Speech and Audio Processing
Volume	6
Issue number	3
DOIs	https://doi.org/10.1109/89.668823
State	Published - 1998

Keywords

Hidden markov model
Isolated syllable
Mandarin chinese
Segmental probability model
Speech recognition

Access to Document

10.1109/89.668823

Cite this

@article{c2ac3bdfb73e474e8165422306084fa0,

title = "Isolated Mandarin base-syllable recognition based upon the segmentai probability model",

abstract = "In this correspondence, a segmental probability model (SPM) is proposed for fast and accurate recognition of the highly confusing isolated Mandarin base-syllables by deleting the state transition probabilities of continuous density hidden Markov models (CHMM), abandoning the dynamic programming process, letting the states equally segment the base-syllables deterministically, and using several special approaches to improve the accuracy and speed. This is achieved by considering the special characteristics of the target vocabulary.",

keywords = "Hidden markov model, Isolated syllable, Mandarin chinese, Segmental probability model, Speech recognition",

author = "Lyu, \{Ren Yuan\} and Hong, \{I. Chung\} and Shen, \{Jia Lin\} and Lee, \{Ming Yu\} and Lee, \{Lin Shan\}",

year = "1998",

doi = "10.1109/89.668823",

language = "英语",

volume = "6",

pages = "293--299",

journal = "IEEE Transactions on Speech and Audio Processing",

issn = "1063-6676",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "3",

}

TY - JOUR

T1 - Isolated Mandarin base-syllable recognition based upon the segmentai probability model

AU - Lyu, Ren Yuan

AU - Hong, I. Chung

AU - Shen, Jia Lin

AU - Lee, Ming Yu

AU - Lee, Lin Shan

PY - 1998

Y1 - 1998

N2 - In this correspondence, a segmental probability model (SPM) is proposed for fast and accurate recognition of the highly confusing isolated Mandarin base-syllables by deleting the state transition probabilities of continuous density hidden Markov models (CHMM), abandoning the dynamic programming process, letting the states equally segment the base-syllables deterministically, and using several special approaches to improve the accuracy and speed. This is achieved by considering the special characteristics of the target vocabulary.

AB - In this correspondence, a segmental probability model (SPM) is proposed for fast and accurate recognition of the highly confusing isolated Mandarin base-syllables by deleting the state transition probabilities of continuous density hidden Markov models (CHMM), abandoning the dynamic programming process, letting the states equally segment the base-syllables deterministically, and using several special approaches to improve the accuracy and speed. This is achieved by considering the special characteristics of the target vocabulary.

KW - Hidden markov model

KW - Isolated syllable

KW - Mandarin chinese

KW - Segmental probability model

KW - Speech recognition

UR - https://www.scopus.com/pages/publications/0032070029

U2 - 10.1109/89.668823

DO - 10.1109/89.668823

M3 - 文章

AN - SCOPUS:0032070029

SN - 1063-6676

VL - 6

SP - 293

EP - 299

JO - IEEE Transactions on Speech and Audio Processing

JF - IEEE Transactions on Speech and Audio Processing

IS - 3

ER -

Isolated Mandarin base-syllable recognition based upon the segmentai probability model

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this