Plug-and-Steer：解耦分离与选择的音视频目标说话人提取
Plug-and-Steer: Decoupling Separation and Selection in Audio-Visual Target Speaker Extraction
AI总结：
提出Plug-and-Steer方法，通过解耦分离与目标选择，利用冻结的纯音频骨干网络和潜引导矩阵实现高保真音视频目标说话人提取。
摘要：
本文的目标是通过解耦分离和目标选择，为音视频目标说话人提取（AV-TSE）提供新视角。传统的AV-TSE系统通常深度融合音频和视觉特征以重新学习整个分离过程，由于野外音视频数据集的噪声特性，这可能会成为保真度的上限。为了解决这个问题，我们提出了Plug-and-Steer，它将高保真分离分配给冻结的纯音频骨干网络，并将视觉模态的作用严格限制在目标选择上。我们引入了潜引导矩阵（LSM），这是一种最小化的线性变换，它重新路由骨干网络内的潜特征，将目标说话人锚定到指定通道。在四种代表性架构上的实验表明，我们的方法有效地保留了不同骨干网络的声学先验，实现了与原始骨干网络相当的可感知质量。音频样本可在以下网址获取：this https URL
英文摘要：
The goal of this paper is to provide a new perspective on audio-visual target speaker extraction (AV-TSE) by decoupling separation and target selection. Conventional AV-TSE systems typically integrate audio and visual features deeply to re-learn the entire separation process, which can act as a fidelity ceiling due to the noisy nature of in-the-wild audio-visual datasets. To address this, we propose Plug-and-Steer, which assigns high-fidelity separation to a frozen audio-only backbone and limits the role of the visual modality strictly to target selection. We introduce the Latent Steering Matrix (LSM), a minimalist linear transformation that re-routes latent features within the backbone to anchor the target speaker to a designated channel. Experiments across four representative architectures show that our method effectively preserves the acoustic priors of diverse backbones, achieving perceptual quality comparable to that of the original backbones. Audio samples are available at: https://plugandsteer.github.io
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。
