Children's Voice Privacy: First Steps And Emerging Challenges

2025-05-30

AI Summary

Children’s speech has long suffered from underrepresentation and heightened privacy vulnerabilities in speech technologies, while existing anonymization research predominantly targets adults and lacks systematic evaluation for children. This paper introduces the first benchmark framework for child speech anonymization, incorporating three child-specific datasets, six state-of-the-art methods—including voice conversion, differential privacy, and speaker disentanglement—and both objective (ASVspoof detection, ASR WER) and subjective (MOS) utility assessments. We find that adult-oriented anonymization methods, though offering baseline privacy protection, substantially degrade speech quality and intelligibility for children. Crucially, automatic evaluation metrics exhibit significant misalignment with human perceptual judgments, exposing their unreliability in child-specific contexts. This work establishes the inaugural systematic benchmark for child speech anonymization, providing essential baselines and methodological guidance for future research.

Technology Category

• Natural Language Processing: Speech
• Machine Learning: Privacy
• Philosophy and Ethics of AI: Privacy & Security

Application Category

• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems

Abstract

Children are one of the most under-represented groups in speech technologies, as well as one of the most vulnerable in terms of privacy. Despite this, anonymization techniques targeting this population have received little attention. In this study, we seek to bridge this gap, and establish a baseline for the use of voice anonymization techniques designed for adult speech when applied to children's voices. Such an evaluation is essential, as children's speech presents a distinct set of challenges when compared to that of adults. This study comprises three children's datasets, six anonymization methods, and objective and subjective utility metrics for evaluation. Our results show that existing systems for adults are still able to protect children's voice privacy, but suffer from much higher utility degradation. In addition, our subjective study displays the challenges of automatic evaluation methods for speech quality in children's speech, highlighting the need for further research.

Problem

• Evaluating adult voice anonymization techniques for children's speech
• Assessing privacy protection and utility degradation in children's voices
• Identifying challenges in automatic speech quality evaluation for children

Innovation

• Evaluates adult voice anonymization on children
• Uses three datasets and six methods
• Highlights need for child-specific research