Abstract
This chapter presents an efficient approach to personalized pronunciation assessment of Taiwaneseaccented English. The main goal of this study is to detect frequently occurring mispronunciation patterns of Taiwanese-accented English instead of scoring English pronunciations directly. The proposed assessment help quickly discover personalized mispronunciations of a student, thus English teachers can spend more time on teaching or rectifying students' pronunciations. In this approach, an unsupervised model adaptation method is performed on the universal acoustic models to recognize the speech of a specific speaker with mispronunciations and Taiwanese accent. A dynamic sentence selection algorithm, considering the mutual information of the related mispronunciations, is proposed to choose a sentence containing the most undetected mispronunciations in order to quickly extract personalized mispronunciations. The experimental results show that the proposed unsupervised adaptation approach obtains an accuracy improvement of about 2.1% on the recognition of Taiwanese-accented English speech.
| Original language | English |
|---|---|
| Title of host publication | Multidisciplinary Computational Intelligence Techniques |
| Subtitle of host publication | Applications in Business, Engineering, and Medicine |
| Publisher | IGI Global |
| Pages | 12-30 |
| Number of pages | 19 |
| ISBN (Print) | 9781466618305 |
| DOIs | |
| Publication status | Published - 2012 Dec 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Computer Science(all)
Cite this
}
Efficient pronunciation assessment of taiwanese-accented english based on unsupervised model adaptation and dynamic sentence selection. / Wu, Chung Hsien; Su, Hung Yu; Liu, Chao Hong.
Multidisciplinary Computational Intelligence Techniques: Applications in Business, Engineering, and Medicine. IGI Global, 2012. p. 12-30.Research output: Chapter in Book/Report/Conference proceeding › Chapter
TY - CHAP
T1 - Efficient pronunciation assessment of taiwanese-accented english based on unsupervised model adaptation and dynamic sentence selection
AU - Wu, Chung Hsien
AU - Su, Hung Yu
AU - Liu, Chao Hong
PY - 2012/12/1
Y1 - 2012/12/1
N2 - This chapter presents an efficient approach to personalized pronunciation assessment of Taiwaneseaccented English. The main goal of this study is to detect frequently occurring mispronunciation patterns of Taiwanese-accented English instead of scoring English pronunciations directly. The proposed assessment help quickly discover personalized mispronunciations of a student, thus English teachers can spend more time on teaching or rectifying students' pronunciations. In this approach, an unsupervised model adaptation method is performed on the universal acoustic models to recognize the speech of a specific speaker with mispronunciations and Taiwanese accent. A dynamic sentence selection algorithm, considering the mutual information of the related mispronunciations, is proposed to choose a sentence containing the most undetected mispronunciations in order to quickly extract personalized mispronunciations. The experimental results show that the proposed unsupervised adaptation approach obtains an accuracy improvement of about 2.1% on the recognition of Taiwanese-accented English speech.
AB - This chapter presents an efficient approach to personalized pronunciation assessment of Taiwaneseaccented English. The main goal of this study is to detect frequently occurring mispronunciation patterns of Taiwanese-accented English instead of scoring English pronunciations directly. The proposed assessment help quickly discover personalized mispronunciations of a student, thus English teachers can spend more time on teaching or rectifying students' pronunciations. In this approach, an unsupervised model adaptation method is performed on the universal acoustic models to recognize the speech of a specific speaker with mispronunciations and Taiwanese accent. A dynamic sentence selection algorithm, considering the mutual information of the related mispronunciations, is proposed to choose a sentence containing the most undetected mispronunciations in order to quickly extract personalized mispronunciations. The experimental results show that the proposed unsupervised adaptation approach obtains an accuracy improvement of about 2.1% on the recognition of Taiwanese-accented English speech.
UR - http://www.scopus.com/inward/record.url?scp=84898207051&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84898207051&partnerID=8YFLogxK
U2 - 10.4018/978-1-4666-1830-5.ch002
DO - 10.4018/978-1-4666-1830-5.ch002
M3 - Chapter
AN - SCOPUS:84898207051
SN - 9781466618305
SP - 12
EP - 30
BT - Multidisciplinary Computational Intelligence Techniques
PB - IGI Global
ER -