Automatic Speech Recognition in Diverse English Accents

Hashir Mohyuddin, Daehan Kwak

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Advancements in automatic speech recognition (ASR) systems have led to their widespread integration into daily life, significantly altering our interaction with technology. However, this interaction is not always seamless for all users. Specifically, speakers with accents frequently face difficulties using ASR technologies and often need to deliberately adjust their pronunciation for better recognition. This study aims to compare leading ASR models' ability to transcribe speech from accented speakers of various nationalities against their native American English-speaking counterparts. We utilize two speech corpora: the L2-ARCTIC (L2A) and the Speech Accent Archive (SAA), which provide the original 'clean' audio samples. From there, two additional files are created by adding background noise to the original samples. These files are then processed through the respective APIs of each ASR model to obtain transcriptions. The accuracy of these transcriptions is then assessed by calculating the Word Error Rate (WER) for each speaker and model. The primary objective of this study is to highlight the challenges faced by speakers with diverse accents in using ASR technology. By highlighting these issues, we aim to encourage proactive measures to take steps towards their resolution. We believe it emphasizes the importance of fostering a more equitable and inclusive user experience.

Original languageEnglish
Title of host publicationProceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages714-718
Number of pages5
ISBN (Electronic)9798350361513
DOIs
StatePublished - 2023
Event2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023 - Las Vegas, United States
Duration: 13 Dec 202315 Dec 2023

Publication series

NameProceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023

Conference

Conference2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023
Country/TerritoryUnited States
CityLas Vegas
Period13/12/2315/12/23

Keywords

  • Accent Recognition
  • Accented Speech
  • ASR Accuracy
  • Automatic Speech Recognition
  • Voice Assistants

Fingerprint

Dive into the research topics of 'Automatic Speech Recognition in Diverse English Accents'. Together they form a unique fingerprint.

Cite this