SyncAI.news, a Varaisys broadcasting
PHONOS: PHOnetic Neutralization for Online Streaming Applications
WQ

Waris Quamer, Mu-Ruei Tseng, Ghady Nasrallah, Ricardo Gutierrez-Osuna

· 1 min read

ResearcharXiv cs.CL

PHONOS: PHOnetic Neutralization for Online Streaming Applications

arXiv:2603.27001v2 Announce Type: replace-cross Abstract: 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 $\leq241\,\mathrm{ms}$ end-to-end latency on a single GPU.

Original source

This story was published by arXiv cs.CL and written by Waris Quamer, Mu-Ruei Tseng, Ghady Nasrallah, Ricardo Gutierrez-Osuna. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News