论文标题
使用基于学习的多帧最小差异无失真响应过滤器的声学回声抑制
Acoustic echo suppression using a learning-based multi-frame minimum variance distortionless response filter
论文作者
论文摘要
声音回声抑制（AES）引起的失真是全双工通信中的常见问题。为了解决失真问题，提出了多帧的最小差异无失真响应（MFMVDR）过滤技术。从深度学习的角度来看，本研究扩展了具有参数估计的MFMVDR滤波器。为了减轻MFMVDR滤波器的数值不稳定性，我们建议直接估计相关矩阵的倒数。 AES系统是有利的，因为不需要双词检测。负尺度不变的信噪比被用作MFMVDR滤波器输出的网络中的损失函数。仿真结果证明了拟议的基于学习的AES系统在双对词，背景噪声和非线性失真条件下的功效。
Distortion resulting from acoustic echo suppression (AES) is a common issue in full-duplex communication. To address the distortion problem, a multi-frame minimum variance distortionless response (MFMVDR) filtering technique is proposed. The MFMVDR filter with parameter estimation which was used in speech enhancement problems is extended in this study from a deep learning perspective. To alleviate numerical instability of the MFMVDR filter, we propose to directly estimate the inverse of the correlation matrix. The AES system is advantageous in that no double-talk detection is required. The negative scale-invariant signal-to-distortion ratio is employed as the loss function in training the network at the output of the MFMVDR filter. Simulation results have demonstrated the efficacy of the proposed learning-based AES system in double-talk, background noise, and nonlinear distortion conditions.
