Pronunciation quality scoring for single syllable word in PSC

Long Zhang; Haifeng Li; Jianhua Wang

doi:10.1007/978-3-642-27866-2_38

Pronunciation quality scoring for single syllable word in PSC

Long Zhang
, Haifeng Li^*
, Jianhua Wang

^*Corresponding author for this work

School of Computer Science and Technology, Harbin Institute of Technology
Harbin Normal University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

This paper discusses pronunciation quality scoring for single syllable word in Putonghua Shuiping Ceshi (PSC) that is a nationwide spoken test to evaluate the standard level and the practical ability that an individual uses the mandarin in china. This study mainly includes some algorithms about the syllable separation, acoustic units selection, posterior probability scoring, threshold values setting and neural network combination. Experiment shows that the proposed approach achieves a high correlation of 0.731, a value very close to 0.786 between human experts. It is also observed that the combination method of neural network gets the best evaluation result. This method is eligible for the automatic scoring in PSC.

Original language	English
Title of host publication	Affective Computing and Intelligent Interaction
Pages	313-319
Number of pages	7
DOIs	https://doi.org/10.1007/978-3-642-27866-2_38
State	Published - 2012
Externally published	Yes
Event	2012 International Conference on Affective Computing and Intelligent Interaction, ICACII 2012 - Taipei, Taiwan, Province of China Duration: 27 Feb 2012 → 28 Feb 2012

Publication series

Name	Advances in Intelligent and Soft Computing
Volume	137 AISC
ISSN (Print)	1867-5662

Conference

Conference	2012 International Conference on Affective Computing and Intelligent Interaction, ICACII 2012
Country/Territory	Taiwan, Province of China
City	Taipei
Period	27/02/12 → 28/02/12

Keywords

HMM
PSC
automatic machine scoring
neural network
pronunciation quality Scoring
single syllable word

Access to Document

10.1007/978-3-642-27866-2_38

Cite this

@inproceedings{adc881ae7100488eb7bacd0c9dad2aa2,

title = "Pronunciation quality scoring for single syllable word in PSC",

abstract = "This paper discusses pronunciation quality scoring for single syllable word in Putonghua Shuiping Ceshi (PSC) that is a nationwide spoken test to evaluate the standard level and the practical ability that an individual uses the mandarin in china. This study mainly includes some algorithms about the syllable separation, acoustic units selection, posterior probability scoring, threshold values setting and neural network combination. Experiment shows that the proposed approach achieves a high correlation of 0.731, a value very close to 0.786 between human experts. It is also observed that the combination method of neural network gets the best evaluation result. This method is eligible for the automatic scoring in PSC.",

keywords = "HMM, PSC, automatic machine scoring, neural network, pronunciation quality Scoring, single syllable word",

author = "Long Zhang and Haifeng Li and Jianhua Wang",

year = "2012",

doi = "10.1007/978-3-642-27866-2\_38",

language = "英语",

isbn = "9783642278655",

series = "Advances in Intelligent and Soft Computing",

pages = "313--319",

booktitle = "Affective Computing and Intelligent Interaction",

note = "2012 International Conference on Affective Computing and Intelligent Interaction, ICACII 2012 ; Conference date: 27-02-2012 Through 28-02-2012",

}

Zhang, L, Li, H & Wang, J 2012, Pronunciation quality scoring for single syllable word in PSC. in Affective Computing and Intelligent Interaction. Advances in Intelligent and Soft Computing, vol. 137 AISC, pp. 313-319, 2012 International Conference on Affective Computing and Intelligent Interaction, ICACII 2012, Taipei, Taiwan, Province of China, 27/02/12. https://doi.org/10.1007/978-3-642-27866-2_38

TY - GEN

T1 - Pronunciation quality scoring for single syllable word in PSC

AU - Zhang, Long

AU - Li, Haifeng

AU - Wang, Jianhua

PY - 2012

Y1 - 2012

N2 - This paper discusses pronunciation quality scoring for single syllable word in Putonghua Shuiping Ceshi (PSC) that is a nationwide spoken test to evaluate the standard level and the practical ability that an individual uses the mandarin in china. This study mainly includes some algorithms about the syllable separation, acoustic units selection, posterior probability scoring, threshold values setting and neural network combination. Experiment shows that the proposed approach achieves a high correlation of 0.731, a value very close to 0.786 between human experts. It is also observed that the combination method of neural network gets the best evaluation result. This method is eligible for the automatic scoring in PSC.

AB - This paper discusses pronunciation quality scoring for single syllable word in Putonghua Shuiping Ceshi (PSC) that is a nationwide spoken test to evaluate the standard level and the practical ability that an individual uses the mandarin in china. This study mainly includes some algorithms about the syllable separation, acoustic units selection, posterior probability scoring, threshold values setting and neural network combination. Experiment shows that the proposed approach achieves a high correlation of 0.731, a value very close to 0.786 between human experts. It is also observed that the combination method of neural network gets the best evaluation result. This method is eligible for the automatic scoring in PSC.

KW - HMM

KW - PSC

KW - automatic machine scoring

KW - neural network

KW - pronunciation quality Scoring

KW - single syllable word

UR - https://www.scopus.com/pages/publications/84860347111

U2 - 10.1007/978-3-642-27866-2_38

DO - 10.1007/978-3-642-27866-2_38

M3 - 会议稿件

AN - SCOPUS:84860347111

SN - 9783642278655

T3 - Advances in Intelligent and Soft Computing

SP - 313

EP - 319

BT - Affective Computing and Intelligent Interaction

T2 - 2012 International Conference on Affective Computing and Intelligent Interaction, ICACII 2012

Y2 - 27 February 2012 through 28 February 2012

ER -

Pronunciation quality scoring for single syllable word in PSC

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this