SLP-L5.5

ADDRESSING GRADIENT MISALIGNMENT IN DATA-AUGMENTED TRAINING FOR ROBUST SPEECH DEEPFAKE DETECTION

Duc-Tuan Truong, Nanyang Technological University, Singapore; Tianchi Liu, National University of Singapore, Singapore; Junjie Li, The Hong Kong Polytechnic University, Hong Kong; Ruijie Tao, National University of Singapore, Singapore; Kong Aik Lee, The Hong Kong Polytechnic University, Hong Kong; Eng Siong Chng, Nanyang Technological University, Singapore
Session:
SLP-L5: Robust Audio Deepfake and Spoofing Detection I Oral
Track:
Speech and Language Processing [SL]
Location:
Room 114
Presentation Time:
Wed, 6 May, 10:20 - 10:40
Session Co-Chairs:
Kong Aik Lee, Associate Professor at The Hong Kong Polytechnic University and Hong-Goo Kang, Professor at Yonsei University
Presentation
Discussion
Resources
No resources available.
Session SLP-L5
SLP-L5.1: SUBGRAPH LOCALIZATION IN THE SUBBANDS FOR PARTIALLY SPOOFED SPEECH DETECTION
Ji Liu, Chenghan Lin, Longbiao Wang, TianJin University, China; Kong Aik Lee, The Hong Kong Polytechnic University, China
SLP-L5.2: THE IMPACT OF AUDIO WATERMARKING ON AUDIO ANTI-SPOOFING COUNTERMEASURES
Zhenshan Zhang, Xueping Zhang, Duke Kunshan University, China; Yechen Wang, Liwei Jin, OfSpectrum, Inc., United States of America; Ming Li, Duke Kunshan University, China
SLP-L5.3: ON DEEPFAKE VOICE DETECTION - IT’S ALL IN THE PRESENTATION
Héctor Delgado, Giorgio Ramondetti, Emanuele Dalmasso, Gennady Karvitsky, Daniele Colibro, Haydar Talib, Microsoft, Spain
SLP-L5.4: COMBINING SSL SPEECH FEATURES, CONTEXTUAL TRANSFORMERS AND MAMBA MODELS FOR REALISTIC AUDIO SPOOFING DETECTION
Luis Buera, Héctor Delgado, Daniele Colibro, Microsoft, Spain; Antonio Miguel, Universidad of Zaragoza, Spain
SLP-L5.5: ADDRESSING GRADIENT MISALIGNMENT IN DATA-AUGMENTED TRAINING FOR ROBUST SPEECH DEEPFAKE DETECTION
Duc-Tuan Truong, Nanyang Technological University, Singapore; Tianchi Liu, National University of Singapore, Singapore; Junjie Li, The Hong Kong Polytechnic University, Hong Kong; Ruijie Tao, National University of Singapore, Singapore; Kong Aik Lee, The Hong Kong Polytechnic University, Hong Kong; Eng Siong Chng, Nanyang Technological University, Singapore
SLP-L5.6: DYNAMIC NOISE-AWARE MULTI LORA FRAMEWORK TOWARDS REAL-WORLD AUDIO DEEPFAKE DETECTION
Woongjae Lee, Hung Dinh-Xuan, Thien-Phuc Doan, Souhwan Jung, Soongsil University, Korea, Republic of
Contacts