Study on performance optimization for Chinese speech retrieval

Tie Ran Zheng; Ji Qing Han; Hai Yang Li

Study on performance optimization for Chinese speech retrieval

Tie Ran Zheng^*
, Ji Qing Han
, Hai Yang Li

^*Corresponding author for this work

School of Computer Science and Technology, Harbin Institute of Technology

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

4 Scopus citations

Abstract

A new unit, named word fragment of language model was proposed to take full advantage of the Chinese linguistic information among adjacent syllables, and an algorithm for word fragment selection was studied. The experimental results show, with the language model based on word fragment, syllable accuracy for recognizer is improved and the speech retrieval system gives better performance than the one with only syllable based model.

Original language	English
Pages (from-to)	84-88
Number of pages	5
Journal	Tongxin Xuebao/Journal on Communications
Volume	30
Issue number	3
State	Published - Mar 2009
Externally published	Yes

Keywords

Chinese speech retrieval
Language model
Lattice
Word fragment

Cite this

@article{2602cf9e2898447196995c6368a9879d,

title = "Study on performance optimization for Chinese speech retrieval",

abstract = "A new unit, named word fragment of language model was proposed to take full advantage of the Chinese linguistic information among adjacent syllables, and an algorithm for word fragment selection was studied. The experimental results show, with the language model based on word fragment, syllable accuracy for recognizer is improved and the speech retrieval system gives better performance than the one with only syllable based model.",

keywords = "Chinese speech retrieval, Language model, Lattice, Word fragment",

author = "Zheng, \{Tie Ran\} and Han, \{Ji Qing\} and Li, \{Hai Yang\}",

year = "2009",

month = mar,

language = "英语",

volume = "30",

pages = "84--88",

journal = "Tongxin Xuebao/Journal on Communications",

issn = "1000-436X",

publisher = "Editorial Board of Journal on Communications",

number = "3",

}

TY - JOUR

T1 - Study on performance optimization for Chinese speech retrieval

AU - Zheng, Tie Ran

AU - Han, Ji Qing

AU - Li, Hai Yang

PY - 2009/3

Y1 - 2009/3

N2 - A new unit, named word fragment of language model was proposed to take full advantage of the Chinese linguistic information among adjacent syllables, and an algorithm for word fragment selection was studied. The experimental results show, with the language model based on word fragment, syllable accuracy for recognizer is improved and the speech retrieval system gives better performance than the one with only syllable based model.

AB - A new unit, named word fragment of language model was proposed to take full advantage of the Chinese linguistic information among adjacent syllables, and an algorithm for word fragment selection was studied. The experimental results show, with the language model based on word fragment, syllable accuracy for recognizer is improved and the speech retrieval system gives better performance than the one with only syllable based model.

KW - Chinese speech retrieval

KW - Language model

KW - Lattice

KW - Word fragment

UR - https://www.scopus.com/pages/publications/64249137502

M3 - 文章

AN - SCOPUS:64249137502

SN - 1000-436X

VL - 30

SP - 84

EP - 88

JO - Tongxin Xuebao/Journal on Communications

JF - Tongxin Xuebao/Journal on Communications

IS - 3

ER -

Study on performance optimization for Chinese speech retrieval

Abstract

Keywords

Other files and links

Fingerprint

Cite this