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 2501.16367eess.AScs.SD
收藏

用于声学回声消除的神经卡尔曼滤波器

Neural Kalman Filters for Acoustic Echo Cancellation

Technische Universität Braunschweig(布伦瑞克工业大学);Carl von Ossietzky University Oldenburg(卡尔·冯·奥西茨基奥尔登堡大学);GN Audio A/S(GN音频公司)

Ernst Seidel, Gerald Enzner, Pejman Mowlaee, Tim Fingscheidt

AI总结:

本文研究了利用深度神经网络支持频域自适应卡尔曼滤波器(FDKF)以克服噪声协方差估计限制,在相同框架下对比了多种神经卡尔曼滤波变体,证明其实现了更快的收敛、更好的回声消除及双讲语音保留。

摘要:

卡尔曼滤波是解决信号处理中各种自适应滤波问题的强大方法。基于声学状态空间概念的频域自适应卡尔曼滤波器(FDKF),为自适应滤波器更新及相关的步长控制提供了统一的解决方案。它最初是为声学回声消除问题而设计的,因此常被应用于免提系统中。本文探讨并简要回顾了线性 FDKF,并研究了如何通过深度神经网络(DNN)以多种方式对其进行进一步支持,特别是为了克服卡尔曼滤波器通常所需的估计过程和观测噪声协方差所带来的挑战与限制。尽管单纯的 FDKF 计算复杂度极低,但其神经卡尔曼滤波器变体可能实现更快的(重新)收敛、更好的回声消除效果,并且在线性和非线性扬声器条件下,甚至在 FDKF 表现优异的双讲近端语音保留方面超越 FDKF。为了提供最新技术的概览,本文在相同的训练框架下并使用相同的数据,对一系列基于 DNN 的 FDKF 扩展进行了比较。

英文摘要:

Kalman filtering is a powerful approach to adaptive filtering for various problems in signal processing. The frequency-domain adaptive Kalman filter (FDKF), based on the concept of the acoustic state space, provides a unifying solution to the adaptive filter update and the related stepsize control. It was conceived for the problem of acoustic echo cancellation and, as such, is frequently applied in hands-free systems. This article motivates and briefly recapitulates the linear FDKF and investigates how it can be further supported by deep neural networks (DNNs) in various ways, specifically to overcome the challenges and limitations related to the usually required estimation of process and observation noise covariances for the Kalman filter. While the mere FDKF comes with very low computational complexity, its neural Kalman filter variants may deliver faster (re)convergence, better echo cancellation, and even exceed the FDKF in its excellent double-talk near-end speech preservation both under linear and nonlinear loudspeaker conditions. To provide a synopsis of the state of the art, this article contributes a comparison of a range of DNN-based extensions of FDKF in the same training framework and using the same data.

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。

↑