基于掩码的波束形成器统一框架内的所有变体都能实现相同的峰值提取性能吗？
Can all variations within the unified mask-based beamformer framework achieve identical peak extraction performance?
AI总结：
本研究针对基于掩码的波束形成器性能争议问题，提出涵盖12种变体的统一框架，通过CHiME-4数据集实验证实所有变体均可达到理论提取性能上限，且掩码缩放可接近理想缩放效果，为目标声音提取系统设计等提供支撑。
摘要：
本研究针对基于掩码的波束形成器（BFs）展开探究，这类波束形成器通过时频掩码估计用于目标声音提取（TSE）的滤波器。尽管已有多种基于掩码的波束形成器被提出，但学界尚未就哪一种具备最优目标提取性能达成共识。此前我们发现，最大信噪比波束形成器与最小均方误差（MSE）波束形成器均可达到与理论上限一致的提取性能，且二者各自对应不同的最优掩码。但仍有两个问题未得到解决：一是仅覆盖了两种波束形成器，未包含最小方差无失真响应波束形成器；二是采用了理想缩放（IS）对输出幅度进行理想调整，该方式不适用于实际场景。\n为解决上述问题，本研究提出了一个基于掩码的波束形成器统一框架，该框架包含两个流程：一是可覆盖所有可能波束形成器的滤波器估计流程，二是通过掩码生成缩放参考、适用于实际场景的缩放流程。根据波束形成器公式中使用的算子和协方差矩阵，所有可能的波束形成器可被划分为12种变体，其中包括两种全新变体。两个流程的最优掩码均通过最小化目标信号与波束形成器输出之间的均方误差（MSE）得到。\n基于CHiME-4数据集的实验结果表明：1）全部12种变体均可达到理论上限性能；2）即便将非负掩码的时间均值约束为1，基于掩码的缩放也能实现与理想缩放（IS）相近的效果。这些结果可通过掩码的实际参数数量加以解释。上述研究发现可为三方面工作提供支撑：一是目标声音提取（TSE）系统的设计，二是通过基于掩码的缩放提升缩放精度，三是波束形成器提取性能的评估。
英文摘要：
This study investigates mask-based beamformers (BFs), which estimate filters for target sound extraction (TSE) using time-frequency masks. Although multiple mask-based BFs have been proposed, no consensus has been reached on which one offers the best target-extraction performance. Previously, we found that maximum signal-to-noise ratio and minimum mean square error (MSE) BFs can achieve the same extraction performance as the theoretical upper-bound performance, with each BF containing a different optimal mask. However, two issues remained unsolved: only two BFs were covered, excluding the minimum variance distortionless response BF, and ideal scaling (IS) was employed to ideally adjust the output scale, which is not applicable to realistic scenarios. To address these issues, this study proposes a unified framework for mask-based BFs comprising two processes: filter estimation that can cover all possible BFs and scaling applicable to realistic scenarios by employing a mask to generate a scaling reference. Based on the operators and covariance matrices used in BF formulas, all possible BFs can be classified into 12 variations, including two new ones. Optimal masks for both processes are obtained by minimizing the MSE between the target and BF output. The experimental results using the CHiME-4 dataset suggested that 1) all 12 variations can achieve the theoretical upper-bound performance, and 2) mask-based scaling can behave like IS, even when constraining the temporal mean of a non-negative mask to one. These results can be explained by considering the practical parameter count of the masks. These findings contribute to 1) designing a TSE system, 2) improving scaling accuracy through mask-based scaling, and 3) estimating the extraction performance of a BF.
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。
