SPE-13.5
EXPLAINING DEEP LEARNING MODELS FOR SPOOFING AND DEEPFAKE DETECTION WITH SHAPLEY ADDITIVE EXPLANATIONS
Wanying Ge, Jose Patino, Massimiliano Todisco, Nicholas Evans, EURECOM, France
Session:
Speaker Recognition II: Anti-Spoofing
Track:
Speech and Language Processing
Location:
Gather Area B
Presentation Time:
Sun, 8 May, 23:00 - 23:45 China Time (UTC +8)
Sun, 8 May, 15:00 - 15:45 UTC
Sun, 8 May, 15:00 - 15:45 UTC
Session Chair:
Elie Khoury, Pindrop
Session SPE-13
SPE-13.1: AASIST: AUDIO ANTI-SPOOFING USING INTEGRATED SPECTRO-TEMPORAL GRAPH ATTENTION NETWORKS
Jee-weon Jung, Hee-Soo Heo, Joon Son Chung, Bong-Jin Lee, Naver Corporation, Korea, Republic of; Hemlata Tak, Nicholas Evans, EURECOM, France; Hye-jin Shim, Ha-Jin Yu, University of Seoul, France
SPE-13.2: ESTIMATING THE CONFIDENCE OF SPEECH SPOOFING COUNTERMEASURE
Xin Wang, Junichi Yamagishi, National Institute of Informatics, Japan
SPE-13.3: TWO-PATH GMM-RESNET AND GMM-SENET FOR ASV SPOOFING DETECTION
Zhenchun Lei, Hui Yan, Changhong Liu, Minglei Ma, Yingen Yang, Jiangxi Normal University, China
SPE-13.4: RAWBOOST: A RAW DATA BOOSTING AND AUGMENTATION METHOD APPLIED TO AUTOMATIC SPEAKER VERIFICATION ANTI-SPOOFING
Hemlata Tak, Madhu Kamble, Jose Patino, Massimiliano Todisco, Nicholas Evans, EURECOM, France
SPE-13.5: EXPLAINING DEEP LEARNING MODELS FOR SPOOFING AND DEEPFAKE DETECTION WITH SHAPLEY ADDITIVE EXPLANATIONS
Wanying Ge, Jose Patino, Massimiliano Todisco, Nicholas Evans, EURECOM, France
SPE-13.6: MULTI-TASK LEARNING IMPROVES SYNTHETIC SPEECH DETECTION
Yichuan Mo, Shilin Wang, Shanghai Jiao Tong University, China