arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.12683eess.AScs.SD
收藏

基于时频参考的端到端波束形成器最优DNN结构研究

Exploring Optimal DNN Architecture for End-to-End Beamformers Based on Time-frequency References

Carnegie Mellon University(卡内基梅隆大学);Sony Corporation(索尼公司)

Yuichiro Koyama, Bhiksha Raj

摘要:

声学波束形成器已被广泛用于增强音频信号。目前,最好的方法是广义特征值和最小方差无失真响应波束形成器的深度神经网络(DNN)变体,以及用于直接计算波束形成滤波器的基于DNN的滤波器估计方法。这两种方法都是有效的;然而,它们在普遍性方面存在盲点。因此,我们提出了一种新的方法,将这两种方法结合到一个单一的框架中,试图利用两者的最佳功能。由此产生的模型称为W-Net波束形成器,包括两个组件;第一个组件计算时频参考,第二个组件用于估计波束形成滤波器。包括各种各样的房间和噪声条件,包括静态和移动噪声源的数据的结果表明,所提出的波束形成器优于其他方法的所有测试的评估指标,这意味着所提出的架构允许有效的计算的波束形成滤波器。

英文摘要:

Acoustic beamformers have been widely used to enhance audio signals. Currently, the best methods are the deep neural network (DNN)-powered variants of the generalized eigenvalue and minimum-variance distortionless response beamformers and the DNN-based filter-estimation methods that are used to directly compute beamforming filters. Both approaches are effective; however, they have blind spots in their generalizability. Therefore, we propose a novel approach for combining these two methods into a single framework that attempts to exploit the best features of both. The resulting model, called the W-Net beamformer, includes two components; the first computes time-frequency references that the second uses to estimate beamforming filters. The results on data that include a wide variety of room and noise conditions, including static and mobile noise sources, show that the proposed beamformer outperforms other methods on all tested evaluation metrics, which signifies that the proposed architecture allows for effective computation of the beamforming filters.

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。

↑