{"total":21,"rows":[{"id":"2109.00648","title":"The VoicePrivacy 2020 Challenge: Results and findings","created":"2021-09-01","cited_by_count":46,"area":null},{"id":"2102.04257","title":"Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communities","created":"2021-02-03","cited_by_count":40,"area":null},{"id":"2202.11823","title":"Differentially Private Speaker Anonymization","created":"2022-02-23","cited_by_count":16,"area":null},{"id":"2212.09006","title":"A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness","created":"2022-12-18","cited_by_count":13,"area":null},{"id":"2310.01128","title":"Disentangling Voice and Content with Self-Supervision for Speaker Recognition","created":"2023-10-02","cited_by_count":13,"area":null},{"id":"2206.09102","title":"Decoupled Federated Learning for ASR with Non-IID Data","created":"2022-06-18","cited_by_count":6,"area":null},{"id":"2104.11051","title":"Protecting gender and identity with disentangled speech representations","created":"2021-04-22","cited_by_count":5,"area":null},{"id":"2206.02797","title":"FedNST: Federated Noisy Student Training for Automatic Speech Recognition","created":"2022-06-06","cited_by_count":5,"area":null},{"id":"2207.01052","title":"Generating gender-ambiguous voices for privacy-preserving speech recognition","created":"2022-07-03","cited_by_count":5,"area":null},{"id":"2301.03206","title":"Introducing Model Inversion Attacks on Automatic Speaker Recognition","created":"2023-01-09","cited_by_count":4,"area":null},{"id":"2601.03783","title":"HearSay Benchmark: Do Audio LLMs Leak What They Hear?","created":"2026-01-07","cited_by_count":3,"area":null},{"id":"2305.00011","title":"Adversarial Representation Learning for Robust Privacy Preservation in Audio","created":"2023-04-29","cited_by_count":2,"area":null},{"id":"2106.02810","title":"An Attribute-Aligned Strategy for Learning Speech Representation","created":"2021-06-05","cited_by_count":1,"area":null},{"id":"2109.11946","title":"Evaluating X-vector-based Speaker Anonymization under White-box Assessment","created":"2021-09-24","cited_by_count":1,"area":null},{"id":"2204.01677","title":"Self-Supervised Speech Representations Preserve Speech Characteristics while Anonymizing Voices","created":"2022-04-04","cited_by_count":1,"area":null},{"id":"2308.04960","title":"Representation Learning for Audio Privacy Preservation using Source Separation and Robust Adversarial Learning","created":"2023-08-09","cited_by_count":1,"area":null},{"id":"2203.09518","title":"Privacy-Preserving Speech Representation Learning using Vector Quantization","created":"2022-03-15","cited_by_count":0,"area":null},{"id":"2211.05446","title":"Privacy-Utility Balanced Voice De-Identification Using Adversarial Examples","created":"2022-11-10","cited_by_count":0,"area":null},{"id":"2306.16071","title":"Long-term Conversation Analysis: Exploring Utility and Privacy","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2403.15510","title":"Privacy-Preserving End-to-End Spoken Language Understanding","created":"2024-03-22","cited_by_count":0,"area":null},{"id":"2507.10194","title":"Learning Private Representations through Entropy-based Adversarial Training","created":"2025-07-14","cited_by_count":0,"area":null}],"next_cursor":null}