A fuzzy pronunciation evaluation model for English learning

Peng Fei Su; Qing Cai Chen; Xiao Long Wang

doi:10.1109/ICMLC.2006.258856

A fuzzy pronunciation evaluation model for English learning

Peng Fei Su^*
, Qing Cai Chen
, Xiao Long Wang

^*Corresponding author for this work

Harbin Institute of Technology Shenzhen

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

2 Scopus citations

Abstract

The evaluation of pronunciation for spoken English is one of the key problems for computer aided spoken language learning. While the most of researchers focus on the improvement of speech recognition to build a reliable evaluation system, there still needs a model that fuses the reliabilities of existing speech processing systems and the learner personalities into the evaluation system. In this paper, the Sugeno integral techniques are introduced to solve this problem. At first, the English phonemes that are hard to be distinguished (HDP) from Chinese language learner are collected and are grouped into different HDP sets. Then, the system reliabilities for distinguishing the phonemes within a HDP set are computed based on the standard speech corpus and are integrated with the phoneme recognition results under the Sugeno integral framework. The fuzzy measures are given for each subset of speech segments that contains at least 10 occurrences of phonemes within a same HDP set. Finally, the linguistic evaluation results are given by the Sugeno integral model based on system reliability and fuzzy measures. The experiment taken on Sphinx-4 shows that, under the 84.7% average recognition rate of the system, our pronunciation evaluation model get reliable and stable results for 3 test corpora.

Original language	English
Title of host publication	Proceedings of the 2006 International Conference on Machine Learning and Cybernetics
Pages	2598-2604
Number of pages	7
DOIs	https://doi.org/10.1109/ICMLC.2006.258856
State	Published - 2006
Externally published	Yes
Event	2006 International Conference on Machine Learning and Cybernetics - Dalian, China Duration: 13 Aug 2006 → 16 Aug 2006

Publication series

Name	Proceedings of the 2006 International Conference on Machine Learning and Cybernetics
Volume	2006

Conference

Conference	2006 International Conference on Machine Learning and Cybernetics
Country/Territory	China
City	Dalian
Period	13/08/06 → 16/08/06

Keywords

Hard to be distinguished phonemes
Pronunciation evaluation
Sphinx-4
Sugeno integral

Access to Document

10.1109/ICMLC.2006.258856

Cite this

@inproceedings{3c487d5f61034bd39574ae795c8e3bab,

title = "A fuzzy pronunciation evaluation model for English learning",

abstract = "The evaluation of pronunciation for spoken English is one of the key problems for computer aided spoken language learning. While the most of researchers focus on the improvement of speech recognition to build a reliable evaluation system, there still needs a model that fuses the reliabilities of existing speech processing systems and the learner personalities into the evaluation system. In this paper, the Sugeno integral techniques are introduced to solve this problem. At first, the English phonemes that are hard to be distinguished (HDP) from Chinese language learner are collected and are grouped into different HDP sets. Then, the system reliabilities for distinguishing the phonemes within a HDP set are computed based on the standard speech corpus and are integrated with the phoneme recognition results under the Sugeno integral framework. The fuzzy measures are given for each subset of speech segments that contains at least 10 occurrences of phonemes within a same HDP set. Finally, the linguistic evaluation results are given by the Sugeno integral model based on system reliability and fuzzy measures. The experiment taken on Sphinx-4 shows that, under the 84.7\% average recognition rate of the system, our pronunciation evaluation model get reliable and stable results for 3 test corpora.",

keywords = "Hard to be distinguished phonemes, Pronunciation evaluation, Sphinx-4, Sugeno integral",

author = "Su, \{Peng Fei\} and Chen, \{Qing Cai\} and Wang, \{Xiao Long\}",

year = "2006",

doi = "10.1109/ICMLC.2006.258856",

language = "英语",

isbn = "1424400619",

series = "Proceedings of the 2006 International Conference on Machine Learning and Cybernetics",

pages = "2598--2604",

booktitle = "Proceedings of the 2006 International Conference on Machine Learning and Cybernetics",

note = "2006 International Conference on Machine Learning and Cybernetics ; Conference date: 13-08-2006 Through 16-08-2006",

}

Su, PF, Chen, QC & Wang, XL 2006, A fuzzy pronunciation evaluation model for English learning. in Proceedings of the 2006 International Conference on Machine Learning and Cybernetics., 4028502, Proceedings of the 2006 International Conference on Machine Learning and Cybernetics, vol. 2006, pp. 2598-2604, 2006 International Conference on Machine Learning and Cybernetics, Dalian, China, 13/08/06. https://doi.org/10.1109/ICMLC.2006.258856

A fuzzy pronunciation evaluation model for English learning. / Su, Peng Fei; Chen, Qing Cai; Wang, Xiao Long.
Proceedings of the 2006 International Conference on Machine Learning and Cybernetics. 2006. p. 2598-2604 4028502 (Proceedings of the 2006 International Conference on Machine Learning and Cybernetics; Vol. 2006).

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

TY - GEN

T1 - A fuzzy pronunciation evaluation model for English learning

AU - Su, Peng Fei

AU - Chen, Qing Cai

AU - Wang, Xiao Long

PY - 2006

Y1 - 2006

N2 - The evaluation of pronunciation for spoken English is one of the key problems for computer aided spoken language learning. While the most of researchers focus on the improvement of speech recognition to build a reliable evaluation system, there still needs a model that fuses the reliabilities of existing speech processing systems and the learner personalities into the evaluation system. In this paper, the Sugeno integral techniques are introduced to solve this problem. At first, the English phonemes that are hard to be distinguished (HDP) from Chinese language learner are collected and are grouped into different HDP sets. Then, the system reliabilities for distinguishing the phonemes within a HDP set are computed based on the standard speech corpus and are integrated with the phoneme recognition results under the Sugeno integral framework. The fuzzy measures are given for each subset of speech segments that contains at least 10 occurrences of phonemes within a same HDP set. Finally, the linguistic evaluation results are given by the Sugeno integral model based on system reliability and fuzzy measures. The experiment taken on Sphinx-4 shows that, under the 84.7% average recognition rate of the system, our pronunciation evaluation model get reliable and stable results for 3 test corpora.

AB - The evaluation of pronunciation for spoken English is one of the key problems for computer aided spoken language learning. While the most of researchers focus on the improvement of speech recognition to build a reliable evaluation system, there still needs a model that fuses the reliabilities of existing speech processing systems and the learner personalities into the evaluation system. In this paper, the Sugeno integral techniques are introduced to solve this problem. At first, the English phonemes that are hard to be distinguished (HDP) from Chinese language learner are collected and are grouped into different HDP sets. Then, the system reliabilities for distinguishing the phonemes within a HDP set are computed based on the standard speech corpus and are integrated with the phoneme recognition results under the Sugeno integral framework. The fuzzy measures are given for each subset of speech segments that contains at least 10 occurrences of phonemes within a same HDP set. Finally, the linguistic evaluation results are given by the Sugeno integral model based on system reliability and fuzzy measures. The experiment taken on Sphinx-4 shows that, under the 84.7% average recognition rate of the system, our pronunciation evaluation model get reliable and stable results for 3 test corpora.

KW - Hard to be distinguished phonemes

KW - Pronunciation evaluation

KW - Sphinx-4

KW - Sugeno integral

UR - https://www.scopus.com/pages/publications/33947253635

U2 - 10.1109/ICMLC.2006.258856

DO - 10.1109/ICMLC.2006.258856

M3 - 会议稿件

AN - SCOPUS:33947253635

SN - 1424400619

SN - 9781424400614

T3 - Proceedings of the 2006 International Conference on Machine Learning and Cybernetics

SP - 2598

EP - 2604

BT - Proceedings of the 2006 International Conference on Machine Learning and Cybernetics

T2 - 2006 International Conference on Machine Learning and Cybernetics

Y2 - 13 August 2006 through 16 August 2006

ER -

A fuzzy pronunciation evaluation model for English learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this