Home > Research > Publications & Outputs > Automatic Sociophonetics

Associated organisational unit

Electronic data

Links

Text available via DOI:

View graph of relations

Automatic Sociophonetics: Exploring corpora using a forensic accent recognition system

Research output: Contribution to journalJournal article

Published

Standard

Automatic Sociophonetics : Exploring corpora using a forensic accent recognition system. / Brown, Georgina; Wormald, Jessica.

In: Journal of the Acoustical Society of America, Vol. 142, No. 1, 31.07.2017, p. 422-433.

Research output: Contribution to journalJournal article

Harvard

Brown, G & Wormald, J 2017, 'Automatic Sociophonetics: Exploring corpora using a forensic accent recognition system', Journal of the Acoustical Society of America, vol. 142, no. 1, pp. 422-433. https://doi.org/10.1121/1.4991330

APA

Brown, G., & Wormald, J. (2017). Automatic Sociophonetics: Exploring corpora using a forensic accent recognition system. Journal of the Acoustical Society of America, 142(1), 422-433. https://doi.org/10.1121/1.4991330

Vancouver

Brown G, Wormald J. Automatic Sociophonetics: Exploring corpora using a forensic accent recognition system. Journal of the Acoustical Society of America. 2017 Jul 31;142(1):422-433. https://doi.org/10.1121/1.4991330

Author

Brown, Georgina ; Wormald, Jessica. / Automatic Sociophonetics : Exploring corpora using a forensic accent recognition system. In: Journal of the Acoustical Society of America. 2017 ; Vol. 142, No. 1. pp. 422-433.

Bibtex

@article{050be552adb6467d9d6e9a84d304e266,
title = "Automatic Sociophonetics: Exploring corpora using a forensic accent recognition system",
abstract = "This paper demonstrates how the Y-ACCDIST system, the York ACCDIST-based automatic accent recognition system [Brown (2015). Proceedings of the International Congress of Phonetic Sciences, Glasgow, UK], can be used to inspect sociophonetic corpora as a preliminary “screening” tool. Although Y-ACCDIST's intended application is to assist with forensic casework, the system can also be exploited in sociophonetic research to begin unpacking variation. Using a subset of the PEBL (Panjabi-English in Bradford and Leicester) corpus, the outputs of Y-ACCDIST are explored, which, it is argued, efficiently and objectively assess speaker similarities across different linguistic varieties. The ways these outputs corroborate with a phonetic analysis of the data are also discovered. First, Y-ACCDIST is used to classify speakers from the corpus based on language background and region. A Y-ACCDIST cluster analysis is then implemented, which groups speakers in ways consistent with more localised networks, providing a means of identifying potential communities of practice. Additionally, the results of a Y-ACCDIST feature selection task that indicates which specific phonemes are most valuable in distinguishing between speaker groups are presented. How Y-ACCDIST outputs can be used to reinforce more traditional sociophonetic analyses and support qualitative interpretations of the data is demonstrated.",
author = "Georgina Brown and Jessica Wormald",
year = "2017",
month = jul
day = "31",
doi = "10.1121/1.4991330",
language = "English",
volume = "142",
pages = "422--433",
journal = "Journal of the Acoustical Society of America",
issn = "0001-4966",
publisher = "Acoustical Society of America",
number = "1",

}

RIS

TY - JOUR

T1 - Automatic Sociophonetics

T2 - Exploring corpora using a forensic accent recognition system

AU - Brown, Georgina

AU - Wormald, Jessica

PY - 2017/7/31

Y1 - 2017/7/31

N2 - This paper demonstrates how the Y-ACCDIST system, the York ACCDIST-based automatic accent recognition system [Brown (2015). Proceedings of the International Congress of Phonetic Sciences, Glasgow, UK], can be used to inspect sociophonetic corpora as a preliminary “screening” tool. Although Y-ACCDIST's intended application is to assist with forensic casework, the system can also be exploited in sociophonetic research to begin unpacking variation. Using a subset of the PEBL (Panjabi-English in Bradford and Leicester) corpus, the outputs of Y-ACCDIST are explored, which, it is argued, efficiently and objectively assess speaker similarities across different linguistic varieties. The ways these outputs corroborate with a phonetic analysis of the data are also discovered. First, Y-ACCDIST is used to classify speakers from the corpus based on language background and region. A Y-ACCDIST cluster analysis is then implemented, which groups speakers in ways consistent with more localised networks, providing a means of identifying potential communities of practice. Additionally, the results of a Y-ACCDIST feature selection task that indicates which specific phonemes are most valuable in distinguishing between speaker groups are presented. How Y-ACCDIST outputs can be used to reinforce more traditional sociophonetic analyses and support qualitative interpretations of the data is demonstrated.

AB - This paper demonstrates how the Y-ACCDIST system, the York ACCDIST-based automatic accent recognition system [Brown (2015). Proceedings of the International Congress of Phonetic Sciences, Glasgow, UK], can be used to inspect sociophonetic corpora as a preliminary “screening” tool. Although Y-ACCDIST's intended application is to assist with forensic casework, the system can also be exploited in sociophonetic research to begin unpacking variation. Using a subset of the PEBL (Panjabi-English in Bradford and Leicester) corpus, the outputs of Y-ACCDIST are explored, which, it is argued, efficiently and objectively assess speaker similarities across different linguistic varieties. The ways these outputs corroborate with a phonetic analysis of the data are also discovered. First, Y-ACCDIST is used to classify speakers from the corpus based on language background and region. A Y-ACCDIST cluster analysis is then implemented, which groups speakers in ways consistent with more localised networks, providing a means of identifying potential communities of practice. Additionally, the results of a Y-ACCDIST feature selection task that indicates which specific phonemes are most valuable in distinguishing between speaker groups are presented. How Y-ACCDIST outputs can be used to reinforce more traditional sociophonetic analyses and support qualitative interpretations of the data is demonstrated.

U2 - 10.1121/1.4991330

DO - 10.1121/1.4991330

M3 - Journal article

VL - 142

SP - 422

EP - 433

JO - Journal of the Acoustical Society of America

JF - Journal of the Acoustical Society of America

SN - 0001-4966

IS - 1

ER -