LiveAnon：基于编解码器语言模型的流式说话人匿名化，提升隐私保护与效用
LiveAnon: Improving Privacy and Utility in Streaming Speaker Anonymization with Codec Language Models
AI总结：
本文提出LiveAnon流式说话人匿名化系统，通过受限RVQ解码降低延迟，在VPC24、VPC26数据集上实现了良好的隐私-效用平衡，优于多数基线系统。
摘要：
说话人匿名化（SA）旨在隐藏说话人身份，同时保留语言内容与情感，但现有流式系统常因离散内容瓶颈丢失情感信息，或需针对情感进行特定建模。本文提出LiveAnon，一种基于语音转换的流式SA系统，直接以预训练流式ASR编码器的隐藏特征为条件，对自回归编解码器语言模型进行建模，无需情感特定监督即可保留情感。为降低编解码器生成延迟，本文引入受限残差向量量化（RVQ）解码，该方法在保留粗码本间依赖关系的同时并行预测其余码本。在VPC24数据集上，LiveAnon相比强基线流式SA系统固定目标Stream-Voice-Anon（SVA）提升了可懂度与情感保留度，在情感保留度上与情感提示SVA相当，且在流式系统中实现了最强的半知情隐私保护；在VPC26数据集上，其在所有评估的匿名化系统的各项指标中排名第二，展现出出色的隐私-效用平衡。
英文摘要：
Speaker anonymization (SA) aims to conceal speaker identity while preserving linguistic content and emotion, but existing streaming systems often lose emotion information through discrete content bottlenecks or require emotion-specific modeling. We present LiveAnon, a voice-conversion-based streaming SA system that directly conditions an autoregressive codec language model on hidden features from a pretrained streaming ASR encoder, preserving emotion without emotion-specific supervision. To reduce codec-generation latency, we introduce capped RVQ decoding, which preserves dependencies among coarse codebooks while predicting the remaining codebooks in parallel. Under VPC24, LiveAnon improves intelligibility and emotion preservation over fixed-target Stream-Voice-Anon (SVA), a strong prior streaming SA system, matches emotion-prompted SVA in emotion preservation, and achieves the strongest semi-informed privacy among streaming systems. Under VPC26, it ranks second across all metrics among the evaluated anonymization systems, demonstrating a strong privacy-utility balance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
