跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2610.39754 · v1

Toward Complete Speaker Anonymization: a Streaming Cascaded System for Voice Privacy and PII Removal

Stanisław KacprzakThomas ThebaudNajim Dehak
cs.SDeess.AS
首次提交 2026-10-29 18:09
版本更新 2026-10-29 18:09
雷达观测 2026-10-30 13:28
arXiv ↗PDF ↗

摘要

We present a cascade streaming voice privacy system, consisting of ASR, NLP, and TTS modules. By leveraging recent improvements in all three aspects of speech and language processing, we show that such a system is capable of achieving a result comparable to state-of-the-art offline voice privacy systems, while providing controllable capabilities of content protection beyond voice. With an estimated utterance-onset end-to-end latency of 717 ms, the presented system preserves speech content with 11% WER on Librispeech, while detecting PII with a 69% SLU F1 score and achieving up to 47.66% EER against a semi-informed attacker.

作者备注：Submitted to ICASSP 2027

查看 arXiv 原文 ↗阅读 PDF ↗

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存，登录后共享已有结果。

版本差异

目前只观测到一个版本，无法比较变化。之后收录新版本时，会在这里对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。

v1 · 2026-10-29 18:09 · 最新观测版本

Toward Complete Speaker Anonymization: a Streaming Cascaded System for Voice Privacy and PII Removal

We present a cascade streaming voice privacy system, consisting of ASR, NLP, and TTS modules. By leveraging recent improvements in all three aspects of speech and language processing, we show that such a system is capable of achieving a result comparable to state-of-the-art offline voice privacy systems, while providing controllable capabilities of content protection beyond voice. With an estimated utterance-onset end-to-end latency of 717 ms, the presented system preserves speech content with 11% WER on Librispeech, while detecting PII with a 69% SLU F1 score and achieving up to 47.66% EER against a semi-informed attacker.

查看此版本解读 →查看此版本原文 ↗