PHONOS: PHOnetic Neutralization for Online Streaming Applications
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915896520343552 |
|---|---|
| author | Quamer, Waris Tseng, Mu-Ruei Nasrallah, Ghady Gutierrez-Osuna, Ricardo |
| author_facet | Quamer, Waris Tseng, Mu-Ruei Nasrallah, Ghady Gutierrez-Osuna, Ricardo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_27001 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PHONOS: PHOnetic Neutralization for Online Streaming Applications Quamer, Waris Tseng, Mu-Ruei Nasrallah, Ghady Gutierrez-Osuna, Ricardo Audio and Speech Processing Computation and Language Machine Learning 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. |
| title | PHONOS: PHOnetic Neutralization for Online Streaming Applications |
| topic | Audio and Speech Processing Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2603.27001 |