The paper delivers a unified framework for fairness in speech technologies by formalizing seven definitions, organizing research into three paradigms, diagnosing pipeline-specific biases, and mapping mitigations to those sources.
On a test of whether one of two random variables is stochastically larger than the other
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
DeCaF combines counterfactual generators and causal models to identify minimal input signal changes that fix CPS failures and derives interpretable assertions that generalize the recovery conditions.
Failure-guided local fuzzing around non-convergent seeds improves detection of faulty HQC configurations over random testing, with concolic seeding adding workload-dependent benefits on VQE versus QAOA.
citing papers explorer
-
Toward Fair Speech Technologies: A Comprehensive Survey of Bias and Fairness in Speech AI
The paper delivers a unified framework for fairness in speech technologies by formalizing seven definitions, organizing research into three paradigms, diagnosing pipeline-specific biases, and mapping mitigations to those sources.
-
Towards Counterfactual Explanation and Assertion Inference for CPS Debugging
DeCaF combines counterfactual generators and causal models to identify minimal input signal changes that fix CPS failures and derives interpretable assertions that generalize the recovery conditions.
-
Failure-Guided Fuzzing for Hybrid Quantum-Classical Programs
Failure-guided local fuzzing around non-convergent seeds improves detection of faulty HQC configurations over random testing, with concolic seeding adding workload-dependent benefits on VQE versus QAOA.