2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

SPE-19: Speaker Recognition 3: Attention and Adversarial

Session Type: Poster
Time: Wednesday, 9 June, 14:00 - 14:45
Location: Gather.Town
 
SPE-19.1: DOUBLE MULTI-HEAD ATTENTION FOR SPEAKER VERIFICATION
         Miquel India Massana; Universitat Politecnica de Catalunya
         Pooyan Safari; Universitat Politecnica de Catalunya
         Javier Hernando; Universitat Politecnica de Catalunya
 
SPE-19.2: GRAPH ATTENTION NETWORKS FOR SPEAKER VERIFICATION
         Jee-weon Jung; University of Seoul
         Hee-Soo Heo; Naver Corporation
         Ha-Jin Yu; University of Seoul
         Joon Son Chung; Naver Corporation
 
SPE-19.3: MEMORY LAYERS WITH MULTI-HEAD ATTENTION MECHANISMS FOR TEXT-DEPENDENT SPEAKER VERIFICATION
         Victoria Mingote; Vivolab - Universidad de Zaragoza
         Antonio Miguel; Vivolab - Universidad de Zaragoza
         Alfonso Ortega; Vivolab - Universidad de Zaragoza
         Eduardo Lleida; Vivolab - Universidad de Zaragoza
 
SPE-19.4: FOOLHD: FOOLING SPEAKER IDENTIFICATION BY HIGHLY IMPERCEPTIBLE ADVERSARIAL DISTURBANCES
         Ali Shahin Shamsabadi; Queen Mary University of London
         Francisco Sepúlveda Teixeira; University of Lisbon
         Alberto Abad; University of Lisbon
         Bhiksha Raj; Carnegie Mellon University
         Andrea Cavallaro; Queen Mary University of London
         Isabel Trancoso; University of Lisbon
 
SPE-19.5: ADVERSARIAL DEFENSE FOR DEEP SPEAKER RECOGNITION USING HYBRID ADVERSARIAL TRAINING
         Monisankha Pal; University of Southern California
         Arindam Jati; University of Southern California
         Raghuveer Peri; University of Southern California
         Chin-Cheng Hsu; University of Southern California
         Wael AbdAlmageed; University of Southern California
         Shrikanth Narayanan; University of Southern California
 
SPE-19.6: DEAAN: DISENTANGLED EMBEDDING AND ADVERSARIAL ADAPTATION NETWORK FOR ROBUST SPEAKER REPRESENTATION LEARNING
         Mufan Sang; University of Texas at Dallas
         Wei Xia; University of Texas at Dallas
         John H.L. Hansen; University of Texas at Dallas