-
摘要: 在噪声环境下, 为提高说话人识别系统的鲁棒性, 需要对系统进行各种抗噪声处理. 本文基于说话人特征的统计特性和直方图均衡化在说话人识别中的应用特点, 提出了直方图均衡化的自适应方法. 实验结果表明, 与普通直方图均衡化变换方法相比, 自适应直方图均衡化能进一步提高辨认系统的辨认率; 并且无论在平稳噪声还是非平稳噪声环境下, 该算法都能取得较好辨认率, 进一步增强系统的鲁棒性.Abstract: Diversified methods of decreasing the influence of noise have appeared to improve the performance of speaker recognition system in noise. In the paper, based on the statistical characteristics of speaker feature and the particularity of histogram equalization applying to speaker recognition, an adaptive histogram equalization method for speaker recognition is presented. The experiments showed improvements in performance with the proposed method in comparison with ordinary histogram equalization, and that the robustness of the system could be improved with the method under different noise environments.
计量
- 文章访问数: 2897
- HTML全文浏览量: 49
- PDF下载量: 1848
- 被引次数: 0