| Home | E-Submission | Sitemap | Editorial Office |  
top_img
Audiology and Speech Research > Volume 22(4); 2026 > Article
Audiology and Speech Research 2026;22(4): 276-280.
Published online: October 31, 2026.
doi: http://doi.org/10.21848/asr.260259
Exploring Artificial Intelligence-Generated Transcripts for Supporting Students Who Are Hard of Hearing: A Preliminary Analysis of Transcription Errors in Subject Lectures
Bong Il Park1,2 , Soo Yong Lee2,3 , Eun-Jin Heo2,4 , Seung-Ah Ahn2 , Hee-Jeong Kim2,4 , Seung-Wook Choi2,5 , Junghwa Bahng2
1Department of Otorhinolaryngology-Head and Neck Surgery, Korea University Anam Hospital, Seoul, Korea
2Department of Audiology and Speech Language Pathology, Hallym University of Graduates Studies, Seoul, Korea
3Employment Development Institute, Korea Employment Agency for Persons with Disabilities (KEAD), Seung Nam, Korea
4Audislab, Seoul, Korea
5Eco Hearing Center-Guro, Seoul, Korea
Correspondence  Junghwa Bahng ,Tel: +82-2-70-8680-6933, Fax: +82-2-70-8680-6933, Email: bahng.jh@gmail.com
Received: September 30, 2026; Revised: October 12, 2026   Accepted: October 12, 2026.  Published online: October 31, 2026.
ABSTRACT
Automatic speech recognition (ASR) may help students who are hard of hearing review spoken explanations, but transcription errors could affect access to course content. This preliminary study examined ASR errors in three Korean EBS lectures (language, mathematics, and chemistry) and an English Technology, Entertainment, Design (TED) talk. Each lecture was played on an iPad in a quiet room and transcribed using Clova Note (Naver Corporation, Seongnam, Korea) and Plaud (Plaud Inc., San Francisco, CA, USA). The outputs were compared with reference transcripts using word error rate (WER) and character error rate (CER). For Korean, WER was calculated using space-delimited eojeols; for English, it was calculated using words. In the Korean language lecture, WERs were 20.27% for Clova Note (Naver Corporation) and 13.85% for Plaud (Plaud Inc.); in mathematics, 42.78% and 54.33%; and in chemistry, 28.62% and 28.44%, respectively. In the TED talk, WERs were 3.88% and 3.10%. In mathematics, the ranking of the two tools differed between WER and CER. Error rates varied across materials and measures, but these data cannot establish comparative performance across languages or benefits for students. Future studies should examine errors in key course content and evaluate how students use verified transcripts to understand lectures.
Key Words: Automatic speech recognition, Hard of hearing students, Educational accessibility, Word error rate, Character error rate
중심단어: 자동 음성 인식, 청각장애 학생, 교육 접근성, 단어 오류율, 문자/음절 오류율
TOOLS
PDF Links  PDF Links
Full text via DOI  Full text via DOI
Download Citation  Download Citation
  Print
Share:      
METRICS
0
Crossref
0
Scopus
345
View
10
Download
Related article
Editorial Office
RN. 8602, Hallym University,
1 Hallymdaehak-gil, Chuncheon-si, Gangwon-do 24252, Korea
TEL: +82-70-8274-4268   FAX: +82-33-256-3420   E-mail: editor@e-asr.org
About |  Browse Articles |  Current Issue |  For Authors
Copyright © Korean Academy of Audiology.                 Developed in M2PI