Robust Adaptive Cancellation of Interfering Speakers for Distributed Microphone Systems in Cars
Robust Adaptive Cancellation of Interfering Speakers for Distributed Microphone Systems in Cars
复制标题
汽车分布式麦克风系统的稳健自适应扬声器干扰消除
DOI：
--
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
T. Wolff
中科院分区：
文献类型：
--
作者：
Timo Matheja;M. Buck;T. Wolff
汽车中的免提系统旨在最佳地捕捉不同说话者的语音。因此，分布式麦克风可以与这些扬声器中的每一个对准，并且可以安装在它们的附近。这种设置的一个应用是优化语音以进行语音识别。希望消除麦克风信号中可能的干扰扬声器的影响[1，2]。对于这个任务，自适应滤波器用于从目标信号中消除干扰信号。与非常类似和公知的回声消除问题相反，噪声分量也出现在滤波器输入信号上。在本文中，提出了一种最佳步长，该步长考虑了用于控制短时频域中的归一化最小均方（NLMS）算法[3]的自适应的噪声分量。还研究了类似于[1]的基于信干比（SIR）的自适应控制。这两种方法的性能进行评估。
Hands-free systems in cars aim to capture the speech of different speakers at the best. Therefor distributed microphones can be aligned to each of these speakers and can be mounted in their vicinity. One application of this setup is to optimize speech for speech recognition. It is desirable to cancel the influence of possible interfering speakers in the microphone signals [1, 2]. For this task an adaptive filter is used to cancel the interfering signal from the target one. In contrast to the very similar and well known echo cancellation problem a noise component also occurs on the filter input signal. In this paper an optimal step size is proposed that considers this noise component for controlling the adaptation of a normalized least mean square (NLMS) algorithm [3] in the short-time frequency domain. A Signal-to-InterferenceRatio (SIR) based adaptation control similar to [1] is also investigated. The performance of both approaches is evaluated.