AegisVox: Factorized Privacy and Clinical Preservation for Long-Form Speech
cs.AI
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/spraphul/aegisvox
Sources
- Content Anonymization for Privacy in Long-form Audio
- HeAR -- Health Acoustic Representations
- SpeechPainter: Text-conditioned Speech Inpainting
- AudioLM: a Language Modeling Approach to Audio Generation
- NouveauVoice: Generating Novel Pseudo Speakers for Voice Anonymization
- F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
- Stream-Voice-Anon: Enhancing Utility of Real-Time Speaker Anonymization via Neural Audio Codec and Language Models
- Qwen3 Technical Report
- Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST
- NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
- EditSpeech: A Text Based Speech Editing System Using Partial Inference and Bidirectional Fusion
- Introducing the VoicePrivacy Initiative
- The VoicePrivacy 2024 Challenge Evaluation Plan
- ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation
- Anonymization, Not Elimination: Utility-Preserved Speech Anonymization
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems