PHONOS: PHOnetic Neutralization for Online Streaming Applications

• URL: http://arxiv.org/abs/2603.27001v1
• Date: Fri, 27 Mar 2026 21:24:18 GMT
• Title: PHONOS: PHOnetic Neutralization for Online Streaming Applications
• Abstract summary: We present PHONOS, a streaming module for real-time speaker anonymization.<n>PHONOS neutralizes non-native accent to sound native-like.<n>Our evaluations show an 81% reduction in non-native accent confidence.
• Score: 4.7828228833826145
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Speaker anonymization (SA) systems modify timbre while leaving regional or non-native accents intact, which is problematic because accents can narrow the anonymity set. To address this issue, we present PHONOS, a streaming module for real-time SA that neutralizes non-native accent to sound native-like. 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 ratings consistent with this shift, and reduced speaker linkability as accent-neutralized utterances move away from the original speaker in embedding space while having latency under 241 ms on single GPU.

Related papers

• TokAN: Accent Normalization Using Self-Supervised Speech Tokens [34.77160718038654]
  TokAN is a token-based accent normalization framework.<n>An autoregressive encoder-decoder model performs token-to-token conversion.<n>A flow-matching synthesizer recovers the Mel-spectrogram from the converted tokens.
  arXiv  Detail & Related papers  (2026-07-04T15:45:38Z)
• Acoustic Cue Alignment in Audio Language Models for Speech Emotion Recognition [58.25449304752214]
  We study whether explicit acoustic cues are grounded when the raw audio is already available.<n>We deriving six interpretable acoustic concept tokens from the standardised eGeMAPS paralinguistic feature set.<n>Aligned tokens improve unweighted average recall (UAR), whereas shuffled, conflicting, or corrupted tokens reduce performance.<n>We argue that token-only interventions provide a practical way to probe audio-grounded cue use, robustness, and interpretability in ALM-based affective computing.
  arXiv  Detail & Related papers  (2026-06-05T14:26:06Z)
• Stream-Voice-Anon: Enhancing Utility of Real-Time Speaker Anonymization via Neural Audio Codec and Language Models [51.7170633585748]
  Stream-Voice-Anon adapts modern causal LM-based NAC architectures specifically for streaming speaker anonymization.<n>Our anonymization approach incorporates pseudo-speaker representation sampling, a speaker embedding mixing and diverse prompt selection strategies.<n>Under the VoicePrivacy 2024 Challenge protocol, Stream-Voice-Anon achieves substantial improvements in intelligibility.
  arXiv  Detail & Related papers  (2026-01-20T13:23:44Z)
• Optimizing Multilingual Text-To-Speech with Accents & Emotions [0.0]
  This paper introduces a new TTS architecture integrating accent along with preserving transliteration with multi-scale emotion modelling.<n>Our approach extends the Parler-TTS model by integrating A language-specific phoneme alignment hybrid encoder-decoder architecture.<n>Tests demonstrate 23.7% improvement in accent accuracy and 85.3% emotion recognition accuracy from native listeners.
  arXiv  Detail & Related papers  (2025-06-19T13:35:05Z)
• Improving Pronunciation and Accent Conversion through Knowledge Distillation And Synthetic Ground-Truth from Native TTS [52.89324095217975]
  Previous approaches on accent conversion mainly aimed at making non-native speech sound more native.<n>We develop a new AC approach that not only focuses on accent conversion but also improves pronunciation of non-native accented speaker.
  arXiv  Detail & Related papers  (2024-10-19T06:12:31Z)
• Accent conversion using discrete units with parallel data synthesized from controllable accented TTS [56.18382038512251]
  The goal of accent conversion (AC) is to convert speech accents while preserving content and speaker identity. Previous methods either required reference utterances during inference, did not preserve speaker identity well, or used one-to-one systems that could only be trained for each non-native accent. This paper presents a promising AC model that can convert many accents into native to overcome these issues.
  arXiv  Detail & Related papers  (2024-09-30T19:52:10Z)
• Accented Speech Recognition With Accent-specific Codebooks [53.288874858671576]
  Speech accents pose a significant challenge to state-of-the-art automatic speech recognition (ASR) systems. Degradation in performance across underrepresented accents is a severe deterrent to the inclusive adoption of ASR. We propose a novel accent adaptation approach for end-to-end ASR systems using cross-attention with a trainable set of codebooks.
  arXiv  Detail & Related papers  (2023-10-24T16:10:58Z)
• DiariST: Streaming Speech Translation with Speaker Diarization [53.595990270899414]
  We propose DiariST, the first streaming ST and SD solution. It is built upon a neural transducer-based streaming ST system and integrates token-level serialized output training and t-vector. Our system achieves a strong ST and SD capability compared to offline systems based on Whisper, while performing streaming inference for overlapping speech.
  arXiv  Detail & Related papers  (2023-09-14T19:33:27Z)
• Improving Accent Conversion with Reference Encoder and End-To-End Text-To-Speech [23.30022534796909]
  Accent conversion (AC) transforms a non-native speaker's accent into a native accent while maintaining the speaker's voice timbre. We propose approaches to improving accent conversion applicability, as well as quality.
  arXiv  Detail & Related papers  (2020-05-19T08:09:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.