@article{ART003236632},
author={Bae Minsoo and Yu Young-Moon},
title={Development of an Open-Source–Based AI Speech-to-Text System and Performance Analysis Using Presidential Speech},
journal={Journal of Korean Society of Archives and Records Management},
issn={1598-1487},
year={2025},
volume={25},
number={3},
pages={243-258},
doi={10.14404/JKSARM.2025.25.3.243}
TY - JOUR
AU - Bae Minsoo
AU - Yu Young-Moon
TI - Development of an Open-Source–Based AI Speech-to-Text System and Performance Analysis Using Presidential Speech
JO - Journal of Korean Society of Archives and Records Management
PY - 2025
VL - 25
IS - 3
PB - Korean Society of Archives and Records Management
SP - 243
EP - 258
SN - 1598-1487
AB - This study developed an open-source–based AI Speech-to-Text (STT) system and analyzed its performance by applying it to presidential speech. While various high-performance STT services are currently commercialized, most are provided online for a fee. However, because of the nature of presidential records, using online services can raise security concerns, and incurring continuous costs for processing accumulating records is inefficient. To address this, the Presidential Archives has developed an offline STT system based on open-source AI models, which is currently under testing and operation. In this study, approximately three hours of presidential audiovisual records were transcribed into text using this function, and the error rate was measured by comparing with the actual text. The results showed that the overall performance is comparable to the latest commercial online services. Additionally, speech rate and recording quality were extracted and analyzed for their correlation with the error rate. Finally, this research highlights the feasibility of applying open-source AI technologies for the utilization of records.
KW - Artificial intelligence;Speech-to-text;Open-source software;Presidential Archives;audiovisual records
DO - 10.14404/JKSARM.2025.25.3.243
ER -
Bae Minsoo and Yu Young-Moon. (2025). Development of an Open-Source–Based AI Speech-to-Text System and Performance Analysis Using Presidential Speech. Journal of Korean Society of Archives and Records Management, 25(3), 243-258.
Bae Minsoo and Yu Young-Moon. 2025, "Development of an Open-Source–Based AI Speech-to-Text System and Performance Analysis Using Presidential Speech", Journal of Korean Society of Archives and Records Management, vol.25, no.3 pp.243-258. Available from: doi:10.14404/JKSARM.2025.25.3.243
Bae Minsoo, Yu Young-Moon "Development of an Open-Source–Based AI Speech-to-Text System and Performance Analysis Using Presidential Speech" Journal of Korean Society of Archives and Records Management 25.3 pp.243-258 (2025) : 243.
Bae Minsoo, Yu Young-Moon. Development of an Open-Source–Based AI Speech-to-Text System and Performance Analysis Using Presidential Speech. 2025; 25(3), 243-258. Available from: doi:10.14404/JKSARM.2025.25.3.243
Bae Minsoo and Yu Young-Moon. "Development of an Open-Source–Based AI Speech-to-Text System and Performance Analysis Using Presidential Speech" Journal of Korean Society of Archives and Records Management 25, no.3 (2025) : 243-258.doi: 10.14404/JKSARM.2025.25.3.243
Bae Minsoo; Yu Young-Moon. Development of an Open-Source–Based AI Speech-to-Text System and Performance Analysis Using Presidential Speech. Journal of Korean Society of Archives and Records Management, 25(3), 243-258. doi: 10.14404/JKSARM.2025.25.3.243
Bae Minsoo; Yu Young-Moon. Development of an Open-Source–Based AI Speech-to-Text System and Performance Analysis Using Presidential Speech. Journal of Korean Society of Archives and Records Management. 2025; 25(3) 243-258. doi: 10.14404/JKSARM.2025.25.3.243
Bae Minsoo, Yu Young-Moon. Development of an Open-Source–Based AI Speech-to-Text System and Performance Analysis Using Presidential Speech. 2025; 25(3), 243-258. Available from: doi:10.14404/JKSARM.2025.25.3.243
Bae Minsoo and Yu Young-Moon. "Development of an Open-Source–Based AI Speech-to-Text System and Performance Analysis Using Presidential Speech" Journal of Korean Society of Archives and Records Management 25, no.3 (2025) : 243-258.doi: 10.14404/JKSARM.2025.25.3.243
