Bias in Automated Speaker Recognition

Toussaint, Wiebke; Ding, Aaron Yi

doi:10.1145/3531146.3533089

Cited by 23 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Biases in audio (used by 18% of included papers) are well-reported in fairness research communities [52,87,129]. UbiComp posed no exception, with such biases surfacing from the included papers.…”

Section: Is Ubicomp Susceptible To Data Biases?mentioning

confidence: 96%

See 1 more Smart Citation

Beyond Accuracy: A Critical Review of Fairness in Machine Learning for Mobile and Wearable Computing

Yfantidou¹,

Constantinides²,

Spathis³

et al. 2023

Preprint

View full text Add to dashboard Cite

The field of mobile, wearable, and ubiquitous computing (UbiComp) is undergoing a revolutionary integration of machine learning. Devices can now diagnose diseases, predict heart irregularities, and unlock the full potential of human cognition. However, the underlying algorithms are not immune to biases with respect to sensitive attributes (e.g., gender, race), leading to discriminatory outcomes. The research communities of HCI and AI-Ethics have recently started to explore ways of reporting information about datasets to surface and, eventually, counter those biases. The goal of this work is to explore the extent to which the UbiComp community has adopted such ways of reporting and highlight potential shortcomings. Through a systematic review of papers published in the Proceedings of the ACM Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT) journal over the past 5 years (2018-2022), we found that progress on algorithmic fairness within the UbiComp community lags behind. Our findings show that only a small portion (5%) of published papers adheres to modern fairness reporting, while the overwhelming majority thereof focuses on accuracy or error metrics. In light of these findings, our work provides practical guidelines for the design and development of ubiquitous technologies that not only strive for accuracy but also for fairness. CCS Concepts: • Human-centered computing → Ubiquitous and mobile computing; • Applied computing → Consumer health; • Computing methodologies → Artificial intelligence; • Social and professional topics → Codes of ethics.

show abstract

Section: Is Ubicomp Susceptible To Data Biases?mentioning

confidence: 96%

“…Yet, UbiComp is far from immune to such discrepancies. Sjoding et al [121] uncovered racial and ethnic biases in pulse oximetry, while Hutiri and Ding [52] reported language biases in speech recognition. Fig.…”

Section: Takeaway #1mentioning

confidence: 99%

Beyond Accuracy: A Critical Review of Fairness in Machine Learning for Mobile and Wearable Computing

Yfantidou¹,

Constantinides²,

Spathis³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Thus, when a decision is made by the AI system, it is very difficult to understand the reasoning behind them and therefore realise if the decision was right or wrong. Moreover, these models are inherently based on the data used for training the model [18]. Thus, they may be prone to data biases, unjustified reasoning, and unethical decision making [19].…”

Section: Introductionmentioning

confidence: 99%

Accountable AI for Healthcare IoT Systems

Bagave

Westberg

Dobbe

et al. 2022

2022 IEEE 4th International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS-ISA)

Self Cite

View full text Add to dashboard Cite

Various AI systems have taken a unique space in our daily lives, helping us in decision-making in critical as well as non-critical scenarios. Although these systems are widely adopted across different sectors, they have not been used to their full potential in critical domains such as the healthcare sector enabled by the Internet of Things (IoT). One of the important hindering factors for adoption is the implication for accountability of decisions and outcomes affected by an AI system, where the term accountability is understood as a means to ensure the performance of a system. However, this term is often interpreted differently in various sectors. Since the EU GDPR regulations and the US congress have emphasised the importance of enabling accountability in AI systems, there is a strong demand to understand and conceptualise this term. It is crucial to address various aspects integrated with accountability and understand how it affects the adoption of AI systems. In this paper, we conceptualise these factors affecting accountability and how it contributes to a trustworthy healthcare AI system. By focusing on healthcare IoT systems, our conceptual mapping will help the readers understand what system aspects those factors are contributing to and how they affect the system trustworthiness. Besides illustrating accountability in detail, we also share our vision towards causal interpretability as a means to enhance accountability for healthcare AI systems. The insights of this paper shall contribute to the knowledge of academic research on accountability, and benefit AI developers and practitioners in the healthcare sector.

show abstract

“…As mandated by GDPR, this study particularly emphasizes privacy and fairness, focusing on gender due to its demonstrated influence on speaker authentication services [9] and the observed gender bias in voice assistant responses [13]. GDPR aims to protect the rights and freedoms of individuals, including privacy and non-discrimination, with regard to personal data processing.…”

Section: Introductionmentioning

confidence: 99%

Privacy-Preserving Voice Anti-Spoofing Using Secure Multi-Party Computation

Chouchane¹,

Brossier²,

Gamboa³

et al. 2021

Interspeech 2021

View full text Add to dashboard Cite

This study investigates the impact of gender information on utility, privacy, and fairness in voice biometric systems, guided by the General Data Protection Regulation (GDPR) mandates, which underscore the need for minimizing the processing and storage of private and sensitive data, and ensuring fairness in automated decision-making systems. We adopt an approach that involves the fine-tuning of the wav2vec 2.0 model for speaker verification tasks, evaluating potential gender-related privacy vulnerabilities in the process. Gender influences during the finetuning process were employed to enhance fairness and privacy in order to emphasise or obscure gender information within the speakers' embeddings. Results from VoxCeleb datasets indicate our adversarial model increases privacy against uninformed attacks, yet slightly diminishes speaker verification performance compared to the non-adversarial model. However, the model's efficacy reduces against informed attacks. Analysis of system performance was conducted to identify potential gender biases, thus highlighting the need for further research to understand and improve the delicate interplay between utility, privacy, and equity in voice biometric systems.

show abstract

Bias in Automated Speaker Recognition

Cited by 23 publications

References 21 publications

Beyond Accuracy: A Critical Review of Fairness in Machine Learning for Mobile and Wearable Computing

Beyond Accuracy: A Critical Review of Fairness in Machine Learning for Mobile and Wearable Computing

Accountable AI for Healthcare IoT Systems

Privacy-Preserving Voice Anti-Spoofing Using Secure Multi-Party Computation

Contact Info

Product

Resources

About