A study of bias mitigation strategies for speaker recognition

Raghuveer Peri, Krishna Somandepalli, Shrikanth Narayanan

Abstract: Highlights•Systematic evaluation of gender biases in speaker verification systems.•Improvements in fairness through data balancing depend on system’s operating point.•Both adversarial and multi-task training improve fairness across operating points.•Multi-task training retains utility, while adversarial training reduces utility.