IEICE TRANSACTIONS on Information
Phoneme Set Design for Speech Recognition of English by Japanese
Summary :
This paper describes a novel method to improve the performance of second language speech recognition when the mother tongue of users is known. Considering that second language speech usually includes less fluent pronunciation and more frequent pronunciation mistakes, the authors propose using a reduced phoneme set generated by a phonetic decision tree (PDT)-based top-down sequential splitting method instead of the canonical one of the second language. The authors verify the efficacy of the proposed method using second language speech collected with a translation game type dialogue-based English CALL system. Experiments show that a speech recognizer achieved higher recognition accuracy with the reduced phoneme set than with the canonical phoneme set.
- Publication
- IEICE TRANSACTIONS on Information Vol.E98-D No.1 pp.148-156
- Publication Date
- 2015/01/01
- Publicized
- 2014/10/01
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2014EDP7168
- Type of Manuscript
- PAPER
- Category
- Speech and Hearing
Authors
Xiaoyun WANG
Doshisha University
Jinsong ZHANG
Beijing Language and Culture University
Masafumi NISHIDA
Doshisha University
Seiichi YAMAMOTO
Doshisha University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Xiaoyun WANG, Jinsong ZHANG, Masafumi NISHIDA, Seiichi YAMAMOTO, "Phoneme Set Design for Speech Recognition of English by Japanese" in IEICE TRANSACTIONS on Information,
vol. E98-D, no. 1, pp. 148-156, January 2015, doi: 10.1587/transinf.2014EDP7168.
Abstract: This paper describes a novel method to improve the performance of second language speech recognition when the mother tongue of users is known. Considering that second language speech usually includes less fluent pronunciation and more frequent pronunciation mistakes, the authors propose using a reduced phoneme set generated by a phonetic decision tree (PDT)-based top-down sequential splitting method instead of the canonical one of the second language. The authors verify the efficacy of the proposed method using second language speech collected with a translation game type dialogue-based English CALL system. Experiments show that a speech recognizer achieved higher recognition accuracy with the reduced phoneme set than with the canonical phoneme set.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2014EDP7168/_p
Copy
@ARTICLE{e98-d_1_148,
author={Xiaoyun WANG, Jinsong ZHANG, Masafumi NISHIDA, Seiichi YAMAMOTO, },
journal={IEICE TRANSACTIONS on Information},
title={Phoneme Set Design for Speech Recognition of English by Japanese},
year={2015},
volume={E98-D},
number={1},
pages={148-156},
abstract={This paper describes a novel method to improve the performance of second language speech recognition when the mother tongue of users is known. Considering that second language speech usually includes less fluent pronunciation and more frequent pronunciation mistakes, the authors propose using a reduced phoneme set generated by a phonetic decision tree (PDT)-based top-down sequential splitting method instead of the canonical one of the second language. The authors verify the efficacy of the proposed method using second language speech collected with a translation game type dialogue-based English CALL system. Experiments show that a speech recognizer achieved higher recognition accuracy with the reduced phoneme set than with the canonical phoneme set.},
keywords={},
doi={10.1587/transinf.2014EDP7168},
ISSN={1745-1361},
month={January},}
Copy
TY - JOUR
TI - Phoneme Set Design for Speech Recognition of English by Japanese
T2 - IEICE TRANSACTIONS on Information
SP - 148
EP - 156
AU - Xiaoyun WANG
AU - Jinsong ZHANG
AU - Masafumi NISHIDA
AU - Seiichi YAMAMOTO
PY - 2015
DO - 10.1587/transinf.2014EDP7168
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2015
AB - This paper describes a novel method to improve the performance of second language speech recognition when the mother tongue of users is known. Considering that second language speech usually includes less fluent pronunciation and more frequent pronunciation mistakes, the authors propose using a reduced phoneme set generated by a phonetic decision tree (PDT)-based top-down sequential splitting method instead of the canonical one of the second language. The authors verify the efficacy of the proposed method using second language speech collected with a translation game type dialogue-based English CALL system. Experiments show that a speech recognizer achieved higher recognition accuracy with the reduced phoneme set than with the canonical phoneme set.
ER -
English
