Pronunciation error detection method based on error rule clustering using a decision tree

Akinori Ito; Yen Ling Lim; Motoyuki Suzuki; Shozo Makino

Pronunciation error detection method based on error rule clustering using a decision tree

Akinori Ito, Yen Ling Lim, Motoyuki Suzuki, Shozo Makino

ENG - Communications Engineering

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

25 Citations (Scopus)

Abstract

We are developing a CALL system to train English pronunciation for Japanese native speakers. However, the precision of the error detection was not very high because the threshold for the detection was not optimum. To improve the detection accuracy, we propose a new method to optimize the thresholds of error detection. The proposed method makes several clusters of the pronunciation error rules, and the thresholds are determined for each cluster. An experiment was carried out to investigate the performance of the proposed method. As a result, about 90% of detection rate was obtained, which is a remarkable improvement from the conventional method.

Original language	English
Pages	173-176
Number of pages	4
Publication status	Published - 2005 Dec 1
Event	9th European Conference on Speech Communication and Technology - Lisbon, Portugal Duration: 2005 Sep 4 → 2005 Sep 8

Other

Other	9th European Conference on Speech Communication and Technology
Country	Portugal
City	Lisbon
Period	05/9/4 → 05/9/8

ASJC Scopus subject areas

Engineering(all)

Access to Document

Fingerprint Dive into the research topics of 'Pronunciation error detection method based on error rule clustering using a decision tree'. Together they form a unique fingerprint.

Cite this

@conference{a03bc8c0666d43aaae15d1a729da8e13,

title = "Pronunciation error detection method based on error rule clustering using a decision tree",

abstract = "We are developing a CALL system to train English pronunciation for Japanese native speakers. However, the precision of the error detection was not very high because the threshold for the detection was not optimum. To improve the detection accuracy, we propose a new method to optimize the thresholds of error detection. The proposed method makes several clusters of the pronunciation error rules, and the thresholds are determined for each cluster. An experiment was carried out to investigate the performance of the proposed method. As a result, about 90% of detection rate was obtained, which is a remarkable improvement from the conventional method.",

author = "Akinori Ito and Lim, {Yen Ling} and Motoyuki Suzuki and Shozo Makino",

year = "2005",

month = dec,

day = "1",

language = "English",

pages = "173--176",

note = "9th European Conference on Speech Communication and Technology ; Conference date: 04-09-2005 Through 08-09-2005",

}

TY - CONF

T1 - Pronunciation error detection method based on error rule clustering using a decision tree

AU - Ito, Akinori

AU - Lim, Yen Ling

AU - Suzuki, Motoyuki

AU - Makino, Shozo

PY - 2005/12/1

Y1 - 2005/12/1

N2 - We are developing a CALL system to train English pronunciation for Japanese native speakers. However, the precision of the error detection was not very high because the threshold for the detection was not optimum. To improve the detection accuracy, we propose a new method to optimize the thresholds of error detection. The proposed method makes several clusters of the pronunciation error rules, and the thresholds are determined for each cluster. An experiment was carried out to investigate the performance of the proposed method. As a result, about 90% of detection rate was obtained, which is a remarkable improvement from the conventional method.

AB - We are developing a CALL system to train English pronunciation for Japanese native speakers. However, the precision of the error detection was not very high because the threshold for the detection was not optimum. To improve the detection accuracy, we propose a new method to optimize the thresholds of error detection. The proposed method makes several clusters of the pronunciation error rules, and the thresholds are determined for each cluster. An experiment was carried out to investigate the performance of the proposed method. As a result, about 90% of detection rate was obtained, which is a remarkable improvement from the conventional method.

UR - http://www.scopus.com/inward/record.url?scp=33745222106&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745222106&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:33745222106

SP - 173

EP - 176

T2 - 9th European Conference on Speech Communication and Technology

Y2 - 4 September 2005 through 8 September 2005

ER -