arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.03058eess.AScs.SD
收藏

面向移动说话人的阵列几何鲁棒基于注意力的神经波束形成器

Array Geometry-Robust Attention-Based Neural Beamformer for Moving Speakers

NTT Corporation(NTT公司);Carl von Ossietzky Universität Oldenburg(奥尔登堡卡尔·冯·奥西茨基大学)

Marvin Tammen, Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani, Shoko Araki, Simon Doclo

AI总结:

本文针对ASA波束形成器对麦克风阵列几何变化敏感的问题,提出随机通道配置训练、变换-平均-拼接和鲁棒输入特征三种方法,在CHiME-3和DEMAND上验证了其对未见阵列下移动说话人的跟踪能力。

摘要:

尽管基于掩蔽的波束形成是一种强大的语音增强方法,但它通常需要手动参数调节来处理移动说话人。最近,该方法通过引入基于注意力的空间协方差矩阵聚合器(ASA)模块得到增强,从而无需手动调节即可准确跟踪移动说话人。然而,该模块中使用的深度神经网络模型仅限于特定的麦克风阵列,对于不同的通道排列、数量或几何结构需要不同的模型。为了提高ASA模块对这些变化的鲁棒性,本文研究了三种方法:使用随机通道配置进行训练、采用变换-平均-拼接方法处理多通道输入特征,以及利用鲁棒输入特征。我们在CHiME-3和DEMAND数据集上的实验表明,这些方法使ASA增强的波束形成器能够在训练中未见过的不同麦克风阵列上跟踪移动说话人。

英文摘要:

Although mask-based beamforming is a powerful speech enhancement approach, it often requires manual parameter tuning to handle moving speakers. Recently, this approach was augmented with an attention-based spatial covariance matrix aggregator (ASA) module, enabling accurate tracking of moving speakers without manual tuning. However, the deep neural network model used in this module is limited to specific microphone arrays, necessitating a different model for varying channel permutations, numbers, or geometries. To improve the robustness of the ASA module against such variations, in this paper we investigate three approaches: training with random channel configurations, employing the transform-average-concatenate method to process multi-channel input features, and utilizing robust input features. Our experiments on the CHiME-3 and DEMAND datasets show that these approaches enable the ASA-augmented beamformer to track moving speakers across different microphone arrays unseen in training.

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。

↑