CHAL-5.4
FAKE AUDIO DETECTION BASED ON UNSUPERVISED PRETRAINING MODELS
Zhiqiang Lv, Shanshan Zhang, Kai Tang, Pengfei Hu, Tencent, China
Session:
Audio Deepfake Detection
Track:
Grand Challenge
Location:
Gather Area B
Presentation Time:
Sat, 7 May, 22:00 - 22:45 China Time (UTC +8)
Sat, 7 May, 14:00 - 14:45 UTC
Sat, 7 May, 14:00 - 14:45 UTC
Session Co-Chairs:
Jianhua Tao, Institute of Automation Chinese Academy of Sciences and Jiangyan Yi, Institute of Automation Chinese Academy of Sciences
Session CHAL-5
CHAL-5.1: ADD 2022: the First Audio Deep Synthesis Detection Challenge
Jiangyan Yi, Ruibo Fu, Jianhua Tao, Shuai Nie, Haoxin Ma, Chenglong Wang, Tao Wang, Zhengkun Tian, Ye Bai, Cunhang Fan, Shan Liang, Shiming Wang, Shuai Zhang, Zhengqi Wen, Institute of Automation, Chinese Academy of Sciences, China; Xinrui Yan, Le Xu, University of Chinese Academy of Sciences, China; Haizhou Li, National University of Singapore, Singapore
CHAL-5.2: Time Domain Adversarial Voice Conversion for ADD 2022
Cheng Wen, Tingwei Guo, Xingjun Tan, Rui Yan, Shuran Zhou, Chuandong Xie, Wei Zou, Xiangang Li, Beike, China
CHAL-5.3: Audio Deepfake Detection System with Neural Stitching for ADD 2022
Rui Yan, Cheng Wen, Shuran Zhou, Tingwei Guo, Wei Zou, Xiangang Li, Beike, China
CHAL-5.4: FAKE AUDIO DETECTION BASED ON UNSUPERVISED PRETRAINING MODELS
Zhiqiang Lv, Shanshan Zhang, Kai Tang, Pengfei Hu, Tencent, China
CHAL-5.5: Partially Fake Audio Detection by Self-attention-based Fake Span Discovery
Haibin Wu, Hung-yi Lee, National Taiwan University, Taiwan; Heng-Cheng Kuo, Kuo-Hsuan Hung, Yu Tsao, Research Center for Information Technology Innovation, Academia Sinica, Taiwan, Taiwan; Naijun Zheng, Helen Meng, The Chinese University of Hong Kong, Hong Kong; Hsin-Min Wang, Institute of Information Science, Academia Sinica, Taiwan, Taiwan
CHAL-5.6: THE VICOMTECH AUDIO DEEPFAKE DETECTION SYSTEM BASED ON WAV2VEC2 FOR THE 2022 ADD CHALLENGE
Juan M. Martín-Doñas, Aitor Álvarez, Vicomtech Foundation, Spain