Automatic Accent and Gender Recognition of Regional UK Speakers

C. Jayne; V. Chang; J. Bailey; Q.A. Xu

doi:10.1007/978-3-031-08223-8_6

Automatic Accent and Gender Recognition of Regional UK Speakers

C. Jayne, V. Chang, J. Bailey, Q.A. Xu

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

With the ubiquity of voice assistants across the UK and the world, speech recognition of the regional accents across the British Isles has proven challenging due to varying pronunciations. This paper proposes an automated recognition of the geographical origin and gender of a voice sample based on the six regional dialects of the United Kingdom. Twenty six features are extracted from 17,877 voice samples and then used to design, implement and evaluate machine learning classifiers based on Artificial Neural Networks (ANNs), Support Vector Machine (SVM), Random Forest (RF) and k-nearest neighbors (k-NN) algorithms. The results suggest that the proposed approach could be applicable for areas such as e-commerce and the service industry, and it provides a contribution to NLP audio research.

Original language	English
Title of host publication	Engineering Applications of Neural Networks - 23rd International Conference, EAAAI/EANN 2022, Proceedings
Editors	Lazaros Iliadis, Chrisina Jayne, Anastasios Tefas, Elias Pimenidis
Publisher	Springer
Pages	67-80
Number of pages	14
Edition	1
ISBN (Electronic)	978-3-031-08223-8
ISBN (Print)	9783031082221
DOIs	https://doi.org/10.1007/978-3-031-08223-8_6
Publication status	Published - 15 Jun 2022

Publication series

Name	Communications in Computer and Information Science
Volume	1600 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Keywords

Accent classification
Artificial neural networks
Deep learning
Speech recognition

Access to Document

10.1007/978-3-031-08223-8_6

Cite this

Jayne, C., Chang, V., Bailey, J., & Xu, Q. A. (2022). Automatic Accent and Gender Recognition of Regional UK Speakers. In L. Iliadis, C. Jayne, A. Tefas, & E. Pimenidis (Eds.), Engineering Applications of Neural Networks - 23rd International Conference, EAAAI/EANN 2022, Proceedings (1 ed., pp. 67-80). (Communications in Computer and Information Science; Vol. 1600 CCIS). Springer. https://doi.org/10.1007/978-3-031-08223-8_6

Jayne, C. ; Chang, V. ; Bailey, J. et al. / Automatic Accent and Gender Recognition of Regional UK Speakers. Engineering Applications of Neural Networks - 23rd International Conference, EAAAI/EANN 2022, Proceedings. editor / Lazaros Iliadis ; Chrisina Jayne ; Anastasios Tefas ; Elias Pimenidis. 1. ed. Springer, 2022. pp. 67-80 (Communications in Computer and Information Science).

@inproceedings{9efbf33ecb264dea8d43ad9ec0a86fe0,

title = "Automatic Accent and Gender Recognition of Regional UK Speakers",

abstract = "With the ubiquity of voice assistants across the UK and the world, speech recognition of the regional accents across the British Isles has proven challenging due to varying pronunciations. This paper proposes an automated recognition of the geographical origin and gender of a voice sample based on the six regional dialects of the United Kingdom. Twenty six features are extracted from 17,877 voice samples and then used to design, implement and evaluate machine learning classifiers based on Artificial Neural Networks (ANNs), Support Vector Machine (SVM), Random Forest (RF) and k-nearest neighbors (k-NN) algorithms. The results suggest that the proposed approach could be applicable for areas such as e-commerce and the service industry, and it provides a contribution to NLP audio research.",

keywords = "Accent classification, Artificial neural networks, Deep learning, Speech recognition",

author = "C. Jayne and V. Chang and J. Bailey and Q.A. Xu",

year = "2022",

month = jun,

day = "15",

doi = "10.1007/978-3-031-08223-8_6",

language = "English",

isbn = "9783031082221",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "67--80",

editor = "Lazaros Iliadis and Chrisina Jayne and Anastasios Tefas and Elias Pimenidis",

booktitle = "Engineering Applications of Neural Networks - 23rd International Conference, EAAAI/EANN 2022, Proceedings",

address = "Germany",

edition = "1",

}

Jayne, C, Chang, V, Bailey, J & Xu, QA 2022, Automatic Accent and Gender Recognition of Regional UK Speakers. in L Iliadis, C Jayne, A Tefas & E Pimenidis (eds), Engineering Applications of Neural Networks - 23rd International Conference, EAAAI/EANN 2022, Proceedings. 1 edn, Communications in Computer and Information Science, vol. 1600 CCIS, Springer, pp. 67-80. https://doi.org/10.1007/978-3-031-08223-8_6

Automatic Accent and Gender Recognition of Regional UK Speakers. / Jayne, C.; Chang, V.; Bailey, J. et al.
Engineering Applications of Neural Networks - 23rd International Conference, EAAAI/EANN 2022, Proceedings. ed. / Lazaros Iliadis; Chrisina Jayne; Anastasios Tefas; Elias Pimenidis. 1. ed. Springer, 2022. p. 67-80 (Communications in Computer and Information Science; Vol. 1600 CCIS).

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - Automatic Accent and Gender Recognition of Regional UK Speakers

AU - Jayne, C.

AU - Chang, V.

AU - Bailey, J.

AU - Xu, Q.A.

PY - 2022/6/15

Y1 - 2022/6/15

N2 - With the ubiquity of voice assistants across the UK and the world, speech recognition of the regional accents across the British Isles has proven challenging due to varying pronunciations. This paper proposes an automated recognition of the geographical origin and gender of a voice sample based on the six regional dialects of the United Kingdom. Twenty six features are extracted from 17,877 voice samples and then used to design, implement and evaluate machine learning classifiers based on Artificial Neural Networks (ANNs), Support Vector Machine (SVM), Random Forest (RF) and k-nearest neighbors (k-NN) algorithms. The results suggest that the proposed approach could be applicable for areas such as e-commerce and the service industry, and it provides a contribution to NLP audio research.

AB - With the ubiquity of voice assistants across the UK and the world, speech recognition of the regional accents across the British Isles has proven challenging due to varying pronunciations. This paper proposes an automated recognition of the geographical origin and gender of a voice sample based on the six regional dialects of the United Kingdom. Twenty six features are extracted from 17,877 voice samples and then used to design, implement and evaluate machine learning classifiers based on Artificial Neural Networks (ANNs), Support Vector Machine (SVM), Random Forest (RF) and k-nearest neighbors (k-NN) algorithms. The results suggest that the proposed approach could be applicable for areas such as e-commerce and the service industry, and it provides a contribution to NLP audio research.

KW - Accent classification

KW - Artificial neural networks

KW - Deep learning

KW - Speech recognition

UR - http://www.scopus.com/inward/record.url?scp=85133025279&partnerID=8YFLogxK

UR - https://link.springer.com/chapter/10.1007/978-3-031-08223-8_6

U2 - 10.1007/978-3-031-08223-8_6

DO - 10.1007/978-3-031-08223-8_6

M3 - Conference publication

SN - 9783031082221

T3 - Communications in Computer and Information Science

SP - 67

EP - 80

BT - Engineering Applications of Neural Networks - 23rd International Conference, EAAAI/EANN 2022, Proceedings

A2 - Iliadis, Lazaros

A2 - Jayne, Chrisina

A2 - Tefas, Anastasios

A2 - Pimenidis, Elias

PB - Springer

ER -

Jayne C, Chang V, Bailey J, Xu QA. Automatic Accent and Gender Recognition of Regional UK Speakers. In Iliadis L, Jayne C, Tefas A, Pimenidis E, editors, Engineering Applications of Neural Networks - 23rd International Conference, EAAAI/EANN 2022, Proceedings. 1 ed. Springer. 2022. p. 67-80. (Communications in Computer and Information Science). doi: 10.1007/978-3-031-08223-8_6