论文部分内容阅读
在噪声环境中如何提高说话人识别精度是说话人识别研究中的一个非常重要的课题。为了让说话人识别系统在安静的环境和噪声环境中都能取得满意的工作性能,研究一个将语音增强器与说话人识别器级连起来的系统。该系统中,采用Weiner滤波增强算法提高说话人识别系统前端预处理的抗噪声能力,提高输入信号的信噪比。实验测试结果表明,该系统具有很好的抗噪声性能。
How to improve speaker recognition accuracy in a noisy environment is a very important issue in speaker recognition research. In order for the speaker recognition system to achieve satisfactory performance in both quiet and noisy environments, a system that connects the speech enhancer to the speaker recognizer is studied. In this system, the Weiner filter enhancement algorithm is used to improve the anti-noise ability of the front-end preprocessing of the speaker recognition system and improve the signal-to-noise ratio of the input signal. Experimental results show that the system has good anti-noise performance.