Relative contribution of vowel quality and duration to native language identification in foreign-accented english

TY - CHAP

T1 - Relative contribution of vowel quality and duration to native language identification in foreign-accented english

AU - Wang, Hongyan

AU - van Heuven, Vincent J.

N1 - Publisher Copyright: © 2018 Association for Computing Machinery.

PY - 2018/3/16

Y1 - 2018/3/16

N2 - Automatic identification of a speaker’s native language background may have forensic applications. This paper explores the feasibility of automatic identification of the native language background of a foreign speaker of English, using phonetically interpretable measurements. The production of the ten monophthongs of (American) English by Dutch, Mandarin Chinese and American speakers was used as a test case. Vowel formants F1 (corresponding to articulatory vowel height), F2 (capturing vowel backness and lip rounding) and vowel duration were extracted. Clearly different duration and patterning of the vowels in the vowel space were seen. Automatic classification of the speaker’s native language was 90 percent correct when all acoustic parameters were used as predictors. Language identification was slightly poorer when only formant data were used (85% correct) and substantially poorer – but much better than chance – when only vowel duration was used (60% correct). We conclude that vowel duration provides a weaker cue to foreign-accent identification in English than the spectral properties but that the combination of both information sources yields the best results.This study was sponsored by the Chinese Ministry of Education Humanities and Social Sciences Planning Project (14YJA740036) and Shenzhen Science and Technology Innovation Committee Basic Research Project (NCYJ 20140418091413526). The second author additionally acknowledges financial support under project TÁMOP 4.2.1.D-15/1KONV-2015-0006 “Development of the innovation centre in Kőszeg in the frame of the educational and research network at the University of Pannonia”, which is subsidized by the European Union and Hungary and co-financed by the European Social Fund.

AB - Automatic identification of a speaker’s native language background may have forensic applications. This paper explores the feasibility of automatic identification of the native language background of a foreign speaker of English, using phonetically interpretable measurements. The production of the ten monophthongs of (American) English by Dutch, Mandarin Chinese and American speakers was used as a test case. Vowel formants F1 (corresponding to articulatory vowel height), F2 (capturing vowel backness and lip rounding) and vowel duration were extracted. Clearly different duration and patterning of the vowels in the vowel space were seen. Automatic classification of the speaker’s native language was 90 percent correct when all acoustic parameters were used as predictors. Language identification was slightly poorer when only formant data were used (85% correct) and substantially poorer – but much better than chance – when only vowel duration was used (60% correct). We conclude that vowel duration provides a weaker cue to foreign-accent identification in English than the spectral properties but that the combination of both information sources yields the best results.This study was sponsored by the Chinese Ministry of Education Humanities and Social Sciences Planning Project (14YJA740036) and Shenzhen Science and Technology Innovation Committee Basic Research Project (NCYJ 20140418091413526). The second author additionally acknowledges financial support under project TÁMOP 4.2.1.D-15/1KONV-2015-0006 “Development of the innovation centre in Kőszeg in the frame of the educational and research network at the University of Pannonia”, which is subsidized by the European Union and Hungary and co-financed by the European Social Fund.

KW - American English

KW - Automatic classification

KW - Dutch

KW - English as a foreign language

KW - Foreign accent identification

KW - Forensic application

KW - Linear Discriminant Analysis (LDA)

KW - Mandarin

KW - Vowel duration

KW - Vowels formants

UR - http://www.scopus.com/inward/record.url?scp=85052020098&partnerID=8YFLogxK

U2 - 10.1145/3199478.3199507

DO - 10.1145/3199478.3199507

M3 - Contribution to conference proceedings

AN - SCOPUS:85052020098

T3 - ACM International Conference Proceeding Series

SP - 16

EP - 20

BT - Proceedings of 2018 the 2nd International Conference on Cryptography, Security and Privacy, ICCSP 2018

PB - Association for Computing Machinery, Inc

T2 - 2nd International Conference on Cryptography, Security and Privacy, ICCSP 2018

Y2 - 16 March 2018 through 18 March 2018

ER -