Language-specific Effects on Automatic Speech Recognition Errors for World Englishes

June Choe; Yiran Chen; May Pik Yu Chan; Aini Li; Xin Gao; Nicole Holliday

Language-specific Effects on Automatic Speech Recognition Errors for World Englishes

June Choe, Yiran Chen, May Pik Yu Chan, Aini Li, Xin Gao, Nicole Holliday

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

18 Citations (Scopus)

15 Downloads (CityUHK Scholars)

Abstract

Despite recent advancements in automated speech recognition (ASR) technologies, reports of unequal performance across speakers of different demographic groups abound. At the same time, the focus on performance metrics such as the Word Error Rate (WER) in prior studies limit the specificity and scope of recommendations that can be offered for system engineering to overcome these challenges. The current study bridges this gap by investigating the performance of Otter’s automatic captioning system on native and non-native English speakers of different language background through a linguistic analysis of segment-level errors. By examining language-specific error profiles for vowels and consonants motivated by linguistic theory, we find that certain categories of errors can be predicted from the phonological structure of a speaker’s native language. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

Original language	English
Title of host publication	Proceedings of the 29th International Conference on Computational Linguistics
Publisher	International Committee on Computational Linguistics
Pages	7177-7186
Publication status	Published - Oct 2022
Externally published	Yes
Event	29th International Conference on Computational Linguistics, COLING 2022 - Gyeongju, Korea, Republic of Duration: 12 Oct 2022 → 17 Oct 2022 https://aclanthology.org/2022.coling-1

Publication series

Name	Proceedings - International Conference on Computational Linguistics, COLING
Publisher	Association for Computational Linguistics (ACL)
ISSN (Print)	2951-2093

Conference

Conference	29th International Conference on Computational Linguistics, COLING 2022
Place	Korea, Republic of
City	Gyeongju
Period	12/10/22 → 17/10/22
Internet address	https://aclanthology.org/2022.coling-1

Publisher's Copyright Statement

This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

Access Output

252697501.pdfFinal Published version, 1.19 MBLicence: CC BY

https://aclanthology.org/2022.coling-1.628/

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Choe, J., Chen, Y., Chan, M. P. Y., Li, A., Gao, X., & Holliday, N. (2022). Language-specific Effects on Automatic Speech Recognition Errors for World Englishes. In Proceedings of the 29th International Conference on Computational Linguistics (pp. 7177-7186). (Proceedings - International Conference on Computational Linguistics, COLING). International Committee on Computational Linguistics. https://aclanthology.org/2022.coling-1.628/

Choe, June ; Chen, Yiran ; Chan, May Pik Yu et al. / Language-specific Effects on Automatic Speech Recognition Errors for World Englishes. Proceedings of the 29th International Conference on Computational Linguistics. International Committee on Computational Linguistics, 2022. pp. 7177-7186 (Proceedings - International Conference on Computational Linguistics, COLING).

@inproceedings{8584083f79e34fb08a64b07e85d9b533,

title = "Language-specific Effects on Automatic Speech Recognition Errors for World Englishes",

abstract = "Despite recent advancements in automated speech recognition (ASR) technologies, reports of unequal performance across speakers of different demographic groups abound. At the same time, the focus on performance metrics such as the Word Error Rate (WER) in prior studies limit the specificity and scope of recommendations that can be offered for system engineering to overcome these challenges. The current study bridges this gap by investigating the performance of Otter{\textquoteright}s automatic captioning system on native and non-native English speakers of different language background through a linguistic analysis of segment-level errors. By examining language-specific error profiles for vowels and consonants motivated by linguistic theory, we find that certain categories of errors can be predicted from the phonological structure of a speaker{\textquoteright}s native language. {\textcopyright} 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.",

author = "June Choe and Yiran Chen and Chan, {May Pik Yu} and Aini Li and Xin Gao and Nicole Holliday",

year = "2022",

month = oct,

language = "English",

series = "Proceedings - International Conference on Computational Linguistics, COLING",

publisher = "International Committee on Computational Linguistics",

pages = "7177--7186",

booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",

note = "29th International Conference on Computational Linguistics, COLING 2022 ; Conference date: 12-10-2022 Through 17-10-2022",

url = "https://aclanthology.org/2022.coling-1",

}

Choe, J, Chen, Y, Chan, MPY, Li, A, Gao, X & Holliday, N 2022, Language-specific Effects on Automatic Speech Recognition Errors for World Englishes. in Proceedings of the 29th International Conference on Computational Linguistics. Proceedings - International Conference on Computational Linguistics, COLING, International Committee on Computational Linguistics, pp. 7177-7186, 29th International Conference on Computational Linguistics, COLING 2022, Gyeongju, Korea, Republic of, 12/10/22. <https://aclanthology.org/2022.coling-1.628/>

Language-specific Effects on Automatic Speech Recognition Errors for World Englishes. / Choe, June; Chen, Yiran; Chan, May Pik Yu et al.
Proceedings of the 29th International Conference on Computational Linguistics. International Committee on Computational Linguistics, 2022. p. 7177-7186 (Proceedings - International Conference on Computational Linguistics, COLING).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Language-specific Effects on Automatic Speech Recognition Errors for World Englishes

AU - Choe, June

AU - Chen, Yiran

AU - Chan, May Pik Yu

AU - Li, Aini

AU - Gao, Xin

AU - Holliday, Nicole

PY - 2022/10

Y1 - 2022/10

N2 - Despite recent advancements in automated speech recognition (ASR) technologies, reports of unequal performance across speakers of different demographic groups abound. At the same time, the focus on performance metrics such as the Word Error Rate (WER) in prior studies limit the specificity and scope of recommendations that can be offered for system engineering to overcome these challenges. The current study bridges this gap by investigating the performance of Otter’s automatic captioning system on native and non-native English speakers of different language background through a linguistic analysis of segment-level errors. By examining language-specific error profiles for vowels and consonants motivated by linguistic theory, we find that certain categories of errors can be predicted from the phonological structure of a speaker’s native language. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

AB - Despite recent advancements in automated speech recognition (ASR) technologies, reports of unequal performance across speakers of different demographic groups abound. At the same time, the focus on performance metrics such as the Word Error Rate (WER) in prior studies limit the specificity and scope of recommendations that can be offered for system engineering to overcome these challenges. The current study bridges this gap by investigating the performance of Otter’s automatic captioning system on native and non-native English speakers of different language background through a linguistic analysis of segment-level errors. By examining language-specific error profiles for vowels and consonants motivated by linguistic theory, we find that certain categories of errors can be predicted from the phonological structure of a speaker’s native language. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

UR - http://www.scopus.com/inward/record.url?scp=85165765390&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85165765390&origin=recordpage

M3 - RGC 32 - Refereed conference paper (with host publication)

T3 - Proceedings - International Conference on Computational Linguistics, COLING

SP - 7177

EP - 7186

BT - Proceedings of the 29th International Conference on Computational Linguistics

PB - International Committee on Computational Linguistics

T2 - 29th International Conference on Computational Linguistics, COLING 2022

Y2 - 12 October 2022 through 17 October 2022

ER -

Choe J, Chen Y, Chan MPY, Li A, Gao X, Holliday N. Language-specific Effects on Automatic Speech Recognition Errors for World Englishes. In Proceedings of the 29th International Conference on Computational Linguistics. International Committee on Computational Linguistics. 2022. p. 7177-7186. (Proceedings - International Conference on Computational Linguistics, COLING).

Language-specific Effects on Automatic Speech Recognition Errors for World Englishes

Abstract

Publication series

Conference

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this