Target speaker extraction (TSE) aims to isolate a specific voice from multiple mixed speakers relying on a registerd sample. Since voiceprint features usually vary greatly, current end-to-end neural networks require large model parameters which are computational intensive and impractical for real-time applications, espetially on resource-constrained platforms. In this paper, we address the TSE task using microphone array and introduce a novel three-stage solution that systematically decouples the process: First, a neural network is trained to estimate the direction of the target speaker. Second, with the direction determined, the Generalized Sidelobe Canceller (GSC) is used to extract the target speech. Third, an Inplace Convolutional Recurrent Neural Network (ICRN) acts as a denoising post-processor, refining the GSC output to yield the final separated speech. Our approach delivers superior performance while drastically reducing computational load, setting a new standard for efficient real-time target speaker extraction.

翻译：目标说话人提取（TSE）旨在基于注册样本从多个混合说话人中分离出特定语音。由于声纹特征通常差异较大，当前端到端神经网络需依赖大量模型参数，导致计算密集且不适用于实时应用，尤其在资源受限平台上。本文利用麦克风阵列处理TSE任务，并提出一种新颖的三阶段方案，系统性地解耦处理流程：首先，训练神经网络估计目标说话人方向；其次，基于确定的方向，采用广义旁瓣对消器（GSC）提取目标语音；最后，利用原位卷积循环神经网络（ICRN）作为去噪后处理器，优化GSC输出以生成最终分离语音。本方法在显著降低计算负载的同时实现了卓越性能，为高效实时目标说话人提取树立了新标准。