Plug-and-Steer: Decoupling Separation and Selection in Audio-Visual Target Speaker Extraction
This addresses audio-visual target speaker extraction for speech processing, with an incremental improvement by preserving acoustic priors in existing backbones.
The paper tackles the problem of audio-visual target speaker extraction by decoupling separation and selection to overcome fidelity limitations from noisy datasets, achieving perceptual quality comparable to original backbones across four architectures.
The goal of this paper is to provide a new perspective on audio-visual target speaker extraction (AV-TSE) by decoupling the 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 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 the original backbones. Audio samples are available at: https://plugandsteer.github.io