ova
Abstract:Speech technology has been increasingly deployed in various areas of daily life including sensitive domains such as healthcare and law enforcement. For these technologies to be effective, they must work reliably for all users while preserving individual privacy. Although tradeoffs between privacy and utility, as well as fairness and utility, have been extensively researched, the specific interplay between privacy and fairness in speech processing remains underexplored. This review and position paper offers an overview of emerging privacy-fairness tradeoffs throughout the entire machine learning lifecycle for speech processing. By drawing on well-established frameworks on fairness and privacy, we examine existing biases and sources of privacy harm that coexist during the development of speech processing models. We then highlight how corresponding privacy-enhancing technologies have the potential to inadvertently increase these biases and how bias mitigation strategies may conversely reduce privacy. By raising open questions, we advocate for a comprehensive evaluation of privacy-fairness tradeoffs for speech technology and the development of privacy-enhancing and fairness-aware algorithms in this domain.
Abstract:In an age of voice-enabled technology, voice anonymization offers a solution to protect people's privacy, provided these systems work equally well across subgroups. This study investigates bias in voice anonymization systems within the context of the Voice Privacy Challenge. We curate a novel benchmark dataset to assess performance disparities among speaker subgroups based on sex and dialect. We analyze the impact of three anonymization systems and attack models on speaker subgroup bias and reveal significant performance variations. Notably, subgroup bias intensifies with advanced attacker capabilities, emphasizing the challenge of achieving equal performance across all subgroups. Our study highlights the need for inclusive benchmark datasets and comprehensive evaluation strategies that address subgroup bias in voice anonymization.
Abstract:Like face recognition, speaker recognition is widely used for voice-based biometric identification in a broad range of industries, including banking, education, recruitment, immigration, law enforcement, healthcare, and well-being. However, while dataset evaluations and audits have improved data practices in computer vision and face recognition, the data practices in speaker recognition have gone largely unquestioned. Our research aims to address this gap by exploring how dataset usage has evolved over time and what implications this has on bias and fairness in speaker recognition systems. Previous studies have demonstrated the presence of historical, representation, and measurement biases in popular speaker recognition benchmarks. In this paper, we present a longitudinal study of speaker recognition datasets used for training and evaluation from 2012 to 2021. We survey close to 700 papers to investigate community adoption of datasets and changes in usage over a crucial time period where speaker recognition approaches transitioned to the widespread adoption of deep neural networks. Our study identifies the most commonly used datasets in the field, examines their usage patterns, and assesses their attributes that affect bias, fairness, and other ethical concerns. Our findings suggest areas for further research on the ethics and fairness of speaker recognition technology.
Abstract:We introduce a novel method to improve the performance of the VoicePrivacy Challenge 2022 baseline B1 variants. Among the known deficiencies of x-vector-based anonymization systems is the insufficient disentangling of the input features. In particular, the fundamental frequency (F0) trajectories, which are used for voice synthesis without any modifications. Especially in cross-gender conversion, this situation causes unnatural sounding voices, increases word error rates (WERs), and personal information leakage. Our submission overcomes this problem by synthesizing an F0 trajectory, which better harmonizes with the anonymized x-vector. We utilized a low-complexity deep neural network to estimate an appropriate F0 value per frame, using the linguistic content from the bottleneck features (BN) and the anonymized x-vector. Our approach results in a significantly improved anonymization system and increased naturalness of the synthesized voice. Consequently, our results suggest that F0 extraction is not required for voice anonymization.