The effect of speech pathology on automatic speaker verification -- a large-scale study

Abstract

Navigating the challenges of data-driven speech processing, one of the primary hurdles is accessing reliable pathological speech data. While public datasets appear to offer solutions, they come with inherent risks of potential unintended exposure of patient health information via re-identification attacks. Using a comprehensive real-world pathological speech corpus, with over n=3,800 test subjects spanning various age groups and speech disorders, we employed a deep-learning-driven automatic speaker verification (ASV) approach. This resulted in a notable mean equal error rate (EER) of 0.89% with a standard deviation of 0.06%, outstripping traditional benchmarks. Our comprehensive assessments demonstrate that pathological speech overall faces heightened privacy breach risks compared to healthy speech. Specifically, adults with dysphonia are at heightened re-identification risks, whereas conditions like dysarthria yield results comparable to those of healthy speakers. Crucially, speech intelligibility does not influence the ASV system's performance metrics. In pediatric cases, particularly those with cleft lip and palate, the recording environment plays a decisive role in re-identification. Merging data across pathological types led to a marked EER decrease, suggesting the potential benefits of pathological diversity in ASV, accompanied by a logarithmic boost in ASV effectiveness. In essence, this research sheds light on the dynamics between pathological speech and speaker verification, emphasizing its crucial role in safeguarding patient confidentiality in our increasingly digitized healthcare era.

Published in Scientific Reports

References in corpus (5)

• The VoicePrivacy 2020 Challenge: Results and findings
• Federated learning for secure development of AI models for Parkinson's disease detection using speech from different languages
• Deep Neural Network for Automatic Assessment of Dysphonia
• Improving Dysarthric Speech Intelligibility Using Cycle-consistent Adversarial Training
• Design Choices for X-vector Based Speaker Anonymization

Cited by in corpus (3)

• Federated learning for secure development of AI models for Parkinson's disease detection using speech from different languages
• The Impact of Speech Anonymization on Pathology and Its Limits
• Differential privacy enables fair and accurate AI-based analysis of speech disorders while protecting patient data