# PHONOS: PHOnetic Neutralization for Online Streaming Applications

arXiv: https://arxiv.org/abs/2603.27001 · HTML: https://mlsanity.com/paper/2603.27001/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 27 Mar 2026.

## Builds on (most cited first, 21 of 21)

- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets](https://mlsanity.com/paper/2104.09494/) (2021)
- [Zero-shot Voice Conversion with Diffusion Transformers](https://mlsanity.com/paper/2411.09943/) (2024)
- [The VoicePrivacy 2024 Challenge Evaluation Plan](https://mlsanity.com/paper/2404.02677/) (2024)
- [Speaker anonymisation using the McAdams coefficient](https://mlsanity.com/paper/2011.01130/) (2020)
- [Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement](https://mlsanity.com/paper/2502.07243/) (2025)
- [Design Choices for X-vector Based Speaker Anonymization](https://mlsanity.com/paper/2005.08601/) (2020)
- [Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy](https://mlsanity.com/paper/2210.07002/) (2022)
- [Convert and Speak: Zero-shot Accent Conversion with Minimum Supervision](https://mlsanity.com/paper/2408.10096/) (2024)
- [End-to-end streaming model for low-latency speech anonymization](https://mlsanity.com/paper/2406.09277/) (2024)
- [GenVC: Self-Supervised Zero-Shot Voice Conversion](https://mlsanity.com/paper/2502.04519/) (2025)
- [DarkStream: real-time speech anonymization with low latency](https://mlsanity.com/paper/2509.04667/) (2025)
- [Stream-Voice-Anon: Enhancing Utility of Real-Time Speaker Anonymization via Neural Audio Codec and Language Models](https://mlsanity.com/paper/2601.13948/) (2026)
- [TVTSyn: Content-Synchronous Time-Varying Timbre for Streaming Voice Conversion and Anonymization](https://mlsanity.com/paper/2602.09389/) (2026)
- [Study on the Fairness of Speaker Verification Systems on Underrepresented Accents in English](https://mlsanity.com/paper/2204.12649/) (2022)
- [Disentangling segmental and prosodic factors to non-native speech comprehensibility](https://mlsanity.com/paper/2408.10997/) (2024)
- [A Pilot Study of GSLM-based Simulation of Foreign Accentuation Only Using Native Speech Corpora](https://mlsanity.com/paper/2407.11370/) (2024)
- [SpeechAccentLLM: A Unified Framework for Foreign Accent Conversion and Text to Speech](https://mlsanity.com/paper/2507.01348/) (2025)
- [Streaming Non-Autoregressive Model for Accent Conversion and Pronunciation Improvement](https://mlsanity.com/paper/2506.16580/) (2025)

## Built on by (most cited first, 1 of 1)

- [AccentCL: Robust Accent Classification with Incremental Expansion](https://mlsanity.com/paper/2610.07426/) (2026)

## Abstract (arXiv)

Speaker anonymization (SA) systems modify timbre while leaving regional or non-native accent cues intact, which is problematic because such cues can reveal a speaker's first-language or geographic background and narrow the anonymity set. To address this issue, we present PHONOS, a streaming module for real-time SA that performs accent neutralization in a privacy sense: reducing accent-origin cues by converting non-native segmental realizations toward a chosen target accent domain. Our approach pre-generates golden speaker utterances that preserve source timbre and rhythm but replace foreign segmentals with native ones using silence-aware DTW alignment and zero-shot voice conversion. These utterances supervise a causal accent translator that maps non-native content tokens to native equivalents with at most 40ms look-ahead, trained using joint cross-entropy and CTC losses. Our evaluations show an 81% reduction in non-native accent confidence, with listening-test accentedness ratings consistent with this shift. PHONOS also moves outputs away from the original speaker in embedding space, suggesting lower linkability under an embedding-based proxy, while running with ≤241,ms end-to-end latency on a single GPU.