Pre-trained self-supervised learning (SSL) models have achieved remarkable success in various speech tasks. However, their potential in target speech extraction (TSE) has not been fully exploited. TSE aims to extract the speech of a target speaker in a mixture guided by enrollment utterances. We exploit pre-trained SSL models for two purposes within a TSE framework, i.e., to process the input mixture and to derive speaker embeddings from the enrollment. In this paper, we focus on how to effectively use SSL models for TSE. We first introduce a novel TSE downstream task following the SUPERB principles. This simple experiment shows the potential of SSL models for TSE, but extraction performance remains far behind the state-of-the-art. We then extend a powerful TSE architecture by incorporating two SSL-based modules: an Adaptive Input Enhancer (AIE) and a speaker encoder. Specifically, the proposed AIE utilizes intermediate representations from the CNN encoder by adjusting the time resolution of CNN encoder and transformer blocks through progressive upsampling, capturing both fine-grained and hierarchical features. Our method outperforms current TSE systems achieving a SI-SDR improvement of 14.0 dB on LibriMix. Moreover, we can further improve performance by 0.7 dB by fine-tuning the whole model including the SSL model parameters.

翻译：预训练自监督学习（SSL）模型在多种语音任务中取得了显著成功。然而，其在目标语音提取（TSE）中的潜力尚未得到充分利用。TSE旨在从混合信号中提取由注册语音引导的目标说话人的语音。我们在TSE框架中利用预训练SSL模型实现两个目标，即处理输入混合信号以及从注册语音中提取说话人嵌入。本文聚焦于如何有效利用SSL模型进行TSE。首先，我们按照SUPERB原则引入一种新颖的TSE下游任务。这一简单实验展示了SSL模型在TSE中的潜力，但其提取性能仍远低于当前最先进水平。随后，我们通过集成两个基于SSL的模块（自适应输入增强器（AIE）和说话人编码器）扩展了一种强大的TSE架构。具体而言，所提出的AIE通过渐进式上采样调整CNN编码器和Transformer模块的时间分辨率，利用CNN编码器的中间表示，同时捕捉细粒度与层次化特征。我们的方法在LibriMix数据集上以14.0 dB的SI-SDR改进超越了当前TSE系统。此外，通过微调包含SSL模型参数的整个模型，我们可进一步将性能提升0.7 dB。