论文部分内容阅读
本文提出了一种用自适应滤波器对语音的混声进行分离的方法。该方法根据自适应消噪原理,利用两只传声器采集多个说话人的混合语音,进行分离试验。试验结果证实了本系统能够对其中所需的说话人的语音信噪比和可懂度有一定程度的改善。
In this paper, we propose a method of separating speech mixing using adaptive filters. According to the principle of adaptive noise canceling, this method uses two microphones to collect the mixed voices of multiple speakers and carries out the separation experiment. The experimental results show that this system can improve the speech signal-to-noise ratio and intelligibility of the speaker required by the system to some extent.