PHONOS: PHOnetic Neutralization for Online Streaming Applications

arXiv:2603.27001 · eess.AS, cs.CL, cs.LG · Submitted 2026-03-27 · Read on arXiv

eess.AS, cs.CL, cs.LG

Submitted: 2026-03-27

Updated: 2026-09-22

Code: https://github.com/snakers4/silero-vad

Project page: https://anonymousis23.github.io/demos

Terminology

• Transformer — 8× in this paper · explained in 2 episodes
• Alignment — 7× in this paper · explained in 1 episode
• Embeddings — 4× in this paper · explained in 2 episodes
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Pseudo-labels — 3× in this paper · explained in 2 episodes
• Quantization — 3× in this paper · explained in 12 episodes
• Anonymity Set — 2× in this paper · explained in 1 episode
• Anonymous Real-Time Speech — 2× in this paper
• IEEE Spoken Language Technology Workshop — 2× in this paper
• Verification — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Causal Inference — 1× in this paper · explained in 4 episodes
• Flow Matching — 1× in this paper · explained in 8 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Intelligence Advanced Research Projects Activity — 1× in this paper
• Robustness — 1× in this paper · explained in 5 episodes
• Two-stage training — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• Verifiability — 1× in this paper · explained in 2 episodes

Sources

• The VoicePrivacy 2024 Challenge Evaluation Plan
• DarkStream: real-time speech anonymization with low latency
• GenVC: Self-Supervised Zero-Shot Voice Conversion
• Stream-Voice-Anon: Enhancing Utility of Real-Time Speaker Anonymization via Neural Audio Codec and Language Models
• SpeechAccentLLM: A Unified Framework for Foreign Accent Conversion and Text to Speech
• Zero-shot Voice Conversion with Diffusion Transformers
• BigVGAN: A Universal Neural Vocoder with Large-Scale Training
• LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech
• F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
• NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets

Related papers

• X-VC: Zero-shot Streaming Voice Conversion in Codec Space
• Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers
• Anonymization, Not Elimination: Utility-Preserved Speech Anonymization
• Towards Audio Token Compression in Large Audio Language Models
• WaveScat: Wavelet Scattering Front-Ends with Self-Supervised Features for Speech Deepfake Detection
• ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions