TA6b5.5

FGSSAT : Unsupervised Fine-Grain Attribution of Unknown Speech Synthesizers Using Transformer Networks

Kratika Bhagtani, Amit Kumar Singh Yadav, Ziyue Xiang, Purdue University, United States; Paolo Bestagini, Politecnico di Milano, Italy; Edward J. Delp, Purdue University, United States

Session:
TA6b5: Computer Vision and Imaging Poster

Track:
Speech, Image and Video Processing

Location:
Fred Farr

Presentation Time:
Tue, 31 Oct, 10:15 - 11:55 PT (UTC -7)

Session Chair:
Guan-Ming Su, Dolby Labs
Presentation
Discussion
Resources
No resources available.
Contacts