Abstract
We present a personalized Korean visual speech recognition (VSR) system and quantify, on the nine-camera OLKAVS corpus, the gap between the population-level benchmark score and an individual user's error. A video-only Conformer initialized from English-trained weights attains 9.95 - 12.19% character error rate (CER) under the corpus protocol against the published 26.64, and 19.00 - 21.52 on unseen wording. Per speaker, CER spans 1.0 to 52.2%, with seen wording lowering CER by 7.0 - 9.0 points and professional delivery and spontaneous speech raising it by 8.5 - 10.5 and 12.7 points. A low-rank adapter with 4.6% of the parameters, trained on 4 to 29 minutes of the user's frontal video, lowers the CER of twelve high-error speakers by 2.13 to 3.58 points, transfers to every camera without loss, and keeps 85% of the full fine-tuning gain at 12% of its cost to other speakers. Cameras above the mouth plane add about six CER points as a constant offset that training on all views keeps small.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Park, S. U., Kim, H., Roh, T., & Park, J. (2026). Personalized Korean Lipreading as Visual Speech Recognition: Transfer, Census and Adaptation on OLKAVS. https://omanscience.com/en/articles/personalized-korean-lipreading-as-visual-speech-recognition-transfer-census-and-adaptation-on-olkavs
MLA 9
Park, Se Un, et al. "Personalized Korean Lipreading as Visual Speech Recognition: Transfer, Census and Adaptation on OLKAVS." https://omanscience.com/en/articles/personalized-korean-lipreading-as-visual-speech-recognition-transfer-census-and-adaptation-on-olkavs.
Chicago (author–date)
Park, Se Un, Hakjun Kim, Taehoon Roh, and Junyoung Park. 2026. "Personalized Korean Lipreading as Visual Speech Recognition: Transfer, Census and Adaptation on OLKAVS." https://omanscience.com/en/articles/personalized-korean-lipreading-as-visual-speech-recognition-transfer-census-and-adaptation-on-olkavs.
Harvard
Park, S. U., Kim, H., Roh, T. and Park, J. (2026) 'Personalized Korean Lipreading as Visual Speech Recognition: Transfer, Census and Adaptation on OLKAVS', Available at: https://omanscience.com/en/articles/personalized-korean-lipreading-as-visual-speech-recognition-transfer-census-and-adaptation-on-olkavs.
Vancouver
Park SU, Kim H, Roh T, Park J. Personalized Korean Lipreading as Visual Speech Recognition: Transfer, Census and Adaptation on OLKAVS. https://omanscience.com/en/articles/personalized-korean-lipreading-as-visual-speech-recognition-transfer-census-and-adaptation-on-olkavs
IEEE
S. U. Park, H. Kim, T. Roh, and J. Park, "Personalized Korean Lipreading as Visual Speech Recognition: Transfer, Census and Adaptation on OLKAVS," https://omanscience.com/en/articles/personalized-korean-lipreading-as-visual-speech-recognition-transfer-census-and-adaptation-on-olkavs.