CAU KU deep fake detection system for ADD 2023 challenge*
- Authors
- Han, Soyul; Kang, Taein; Choi, Sunmook; Seo, Jaejin; Chung, Sanghyeok; Lee, Sumi; Oh, Seungsang; Kwak, Il-Youp
- Issue Date
- 2023
- Publisher
- CEUR-WS
- Keywords
- audio deep synthesis; audio deepfake detection; deep learning; deepfake algorithm recognition
- Citation
- CEUR Workshop Proceedings, v.3597, pp 23 - 30
- Pages
- 8
- Journal Title
- CEUR Workshop Proceedings
- Volume
- 3597
- Start Page
- 23
- End Page
- 30
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/72711
- ISSN
- 1613-0073
- Abstract
- The paper presents the participation of the CAU_KU team in the ADD 2023 Challenge, specifically in track 1.2 (audio fake game - detection track) and track 3 (deepfake algorithm recognition track). Various deep learning models were explored using features from the pretrained wav2vec2 network, as well as CQT, mel-spectrogram, etc. We modified the representation extraction component of the AASIST model to incorporate 2D spectrograms (wav2vec2 or CQT) and attempted different deep learning models, with model ensembling employed to create the final model. For track 1.2, our submitted ensemble model for round 1 utilized the CQT-LCNN and CQT-AASIST models. For round 2, our model used the CQT-LCNN, CQT-AASIST, and W2V2-GMM models. For track 3, we ensembled the CQT-LCNN, CQT-OFD and AASIST models. Additionally, we applied the openmax algorithm to detect unknown deepfake attacks. Our best submission achieved 23.44% and 21.26% on round 1 and 2 of track 1.2, respectively, and ranked 3rd in track 1.2. © 2023 CEUR-WS. All rights reserved.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - ETC > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.