paper-with-me

홈 › Papers

To train or not to train adversarially: A study of bias mitigation strategies for speaker recognition

2022-03-17 · Raghuveer Peri, Krishna Somandepalli, Shrikanth Narayanan

Speaker recognition is increasingly used in several everyday applications including smart speakers, customer care centers and other speech-driven analytics. It is crucial to accurately evaluate and mitigate biases present in machine learning (ML) based speech technologies, such as speaker recognition, to ensure their inclusive adoption. ML fairness studies with respect to various demographic factors in modern speaker recognition systems are lagging compared to other human-centered applications such as face recognition. Existing studies on fairness in speaker recognition systems are largely limited to evaluating biases at specific operating points of the systems, which can lead to false expectations of fairness. Moreover, there are only a handful of bias mitigation strategies developed for speaker recognition systems. In this paper, we systematically evaluate the biases present in speaker recognition systems with respect to gender across a range of system operating points. We also propose adversarial and multi-task learning techniques to improve the fairness of these systems. We show through quantitative and qualitative evaluations that the proposed methods improve the fairness of ASV systems over baseline methods trained using data balancing techniques. We also present a fairness-utility trade-off analysis to jointly examine fairness and the overall system performance. We show that although systems trained using adversarial techniques improve fairness, they are prone to reduced utility. On the other hand, multi-task methods can improve the fairness while retaining the utility. These findings can inform the choice of bias mitigation strategies in the field of speaker recognition.

📄 PDF Abstract BibTeX arXiv:2203.09122

Code (1)

rperi/trustworthy-asv-fairness 공식 구현 pytorch

Tasks

Face RecognitionFairnessMulti-Task LearningSpeaker Recognition

Similar Papers 제목 키워드 기반

Bias Testing and Mitigation in Black Box LLMs using Metamorphic Relations

2025-11-29 · Sina Salimian, Gias Uddin, Sumon Biswas, Henry Leung arxiv

The widespread deployment of Large Language Models (LLMs) has intensified concerns about subtle social biases embedded in their outputs. Existing guardrails often fail when faced with indirect or contextually complex bia…

No Free Lunch in Language Model Bias Mitigation? Targeted Bias Reduction Can Exacerbate Unmitigated LLM Biases

2025-11-23 · Shireen Chand, Faith Baca, Emilio Ferrara arxiv

Large Language Models (LLMs) inherit societal biases from their training data, potentially leading to harmful or unfair outputs. While various techniques aim to mitigate these biases, their effects are often evaluated on…

A Comprehensive Empirical Study of Bias Mitigation Methods for Machine Learning Classifiers

2022-07-07 · Zhenpeng Chen, Jie M. Zhang, Federica Sarro, Mark Harman

Software bias is an increasingly important operational concern for software engineers. We present a large-scale, comprehensive empirical study of 17 representative bias mitigation methods for Machine Learning (ML) classi…

Fairness

Failing on Bias Mitigation: A Case Study on the Challenges of Fairness in Government Data

2026-01-21 · Hongbo Bo, Jingyu Hu, Debbie Watson, Weiru Liu arxiv

The potential for bias and unfairness in AI-supporting government services raises ethical and legal concerns. Using crime rate prediction with the Bristol City Council data as a case study, we examine how these issues pe…

Toward Understanding Bias Correlations for Mitigation in NLP

2022-05-24 · Lu Cheng, Suyu Ge, Huan Liu

Natural Language Processing (NLP) models have been found discriminative against groups of different social identities such as gender and race. With the negative consequences of these undesired biases, researchers have re…

FairnessWord Embeddings